# lobehub v2.2.15 — 🚀 Release v2.2.15

- Product: lobehub (https://whatsnew.fyi/product/lobehub)
- Vendor: lobehub
- Date: 2026-08-28
- Version: v2.2.15
- Original notes: https://github.com/lobehub/lobehub/releases/tag/v2.2.15
- Permalink: https://whatsnew.fyi/product/lobehub/releases/v2.2.15

What's New is an index, not a publisher: every entry below links to the vendor's own release notes, which are the authoritative source. Entries are labelled where they are hand-curated sample data, pre-releases, or drawn from a secondary source such as a developer blog.

Reuse: the summaries, labels and curation here are © What's New. Quote freely with attribution and a link back; wholesale republication of the corpus is not permitted — terms: https://whatsnew.fyi/terms. The vendors' own release notes remain their publishers'.

---

- **added** — Provider-backed heterogeneous Agents with Claude Code and Codex gaining deployment-backed model options
- **added** — Kimi Code and Pi add new provider paths across web and Desktop
- **added** — Restart-free Desktop updates with signed renderer updates, compatibility checks, compressed delta delivery, and automatic rollback
- **added** — Agent approval and intervention flows that align across surfaces with generic interventions persisting for long-running work
- **added** — Agent self-learning with Labs-gated growth portrait showing learned domains, rules, and practice history
- **added** — Public Artifacts and Workbench allowing local HTML and site assets to be packaged into versioned Artifacts
- **added** — Workspace collaboration features including per-member Resource grants and transfer requests
- **added** — Redesigned Notification Center for workspace management
- **added** — Global interface font setting and locale-aware font stacks
- **added** — Scheduled Tasks get a dedicated view with successful subtasks completing automatically
- **added** — Self-learning gains dedicated domain creation, editable anchors, and operation-scoped Context
- **added** — Agent profiles gain a character sheet and reusable full-body artwork
- **added** — Cursor moves to bidirectional ACP session with permission prompts, questions, approvals, and safe resume recovery
- **added** — macOS communication notifications include Agent avatars
- **added** — Realtime voice dictation adds finalized speech to editable draft without auto-sending
- **changed** — Goal state moves to durable graph with dependency-aware scheduling, CLI controls, and autonomous recovery
- **changed** — Each Topic keeps its own heterogeneous model choice instead of rewriting the Agent default
- **changed** — Home restores marketing hierarchy, consolidates promotional surfaces, and sharpens recommendation visuals
- **fixed** — Dead Topic locks no longer swallow sent messages
- **fixed** — Completed gateway runs clear stale loading state in the sidebar

##### 📦 Release v2.2.15

This release was automatically published from PR #18747.

###### Changes
See PR description: https://github.com/lobehub/lobehub/pull/18747

###### Commit Message
#### 🚀 LobeHub Release (20260827)

**Release Date:** August 27, 2026  
**Since v2.2.14:** 235 merged PRs · 13 contributors

> This cycle makes long-running Agent work easier to direct and recover, expands provider-backed heterogeneous Agents, delivers safer restart-free Desktop updates, and deepens Artifact, Workspace, and acceptance workflows.

---

##### ✨ Highlights

- **Provider-backed heterogeneous Agents** — Claude Code and Codex gain deployment-backed model options, while Kimi Code and Pi add new provider paths across web and Desktop. (#18468, #18558, #18609, #18658, #18720, #18721)
- **Restart-free Desktop updates** — Signed renderer updates apply in place with compatibility checks, compressed delta delivery, release-scoped artifacts, and automatic rollback. (#18648, #18694, #18716, #18724)
- **Agent approval and intervention flows** — Agent approvals now align across surfaces, and generic interventions persist so long-running work can resume with the right user decision. (#18417, #18645)
- **Agent self-learning** — A Labs-gated growth portrait shows learned domains, rules, and practice history while operation-scoped expertise improves future Work. (#18195, #18394, #18420)
- **Public Artifacts and Workbench** — Local HTML and site assets can be packaged into versioned Artifacts, while acceptance and verification run in a standalone SSR Workbench. (#18424, #18473, #18569, #18728)
- **Workspace collaboration** — Per-member Resource grants, transfer requests, and a redesigned Notification Center make shared work easier to control and act on. (#18389, #18432, #18536, #18545)
- **More adaptable everyday UI** — Global interface fonts, consolidated Home promotions, clearer model availability, and refined recommendation visuals make the app easier to personalize and navigate. (#18712, #18722, #18730, #18741)

---

##### 🏗️ Core Agent & Architecture

###### Goals, Tasks & Acceptance

- Goal state moves to a durable graph with dependency-aware scheduling, CLI controls, autonomous recovery, and terminal Acceptance Work. (#18574, #18597, #18635)
- Scheduled Tasks get a dedicated view, successful subtasks complete automatically, and Kanban grouping matches the list view with clearer loading states. (#18586, #18591, #18631, #18707)
- Acceptance deliveries group by Project and can be merged without losing checks, evidence, or prior review decisions; the review round now always reports its outcome. (#18448, #18537, #18548, #18672)
- Acceptance features now share one consistent product boundary, while abandoned Goal Work and stale scoped tool calls recover instead of silently ending the run. (#18656, #18664, #18703)

###### Agent Learning & Identity

- Self-learning gains dedicated domain creation, editable anchors, operation-scoped Context, and safer lesson history management. (#18418, #18420, #18517, #18556)
- Agent profiles gain a character sheet and reusable full-body artwork that retains its style and direction. (#18446, #18464)
- Agent authors can restrict Topic sharing, while Agent transfers preserve accumulated expertise. (#18445, #18557)
- Approval workflows align with web behavior, and generic interventions persist across Agent runs. (#18417, #18645)

---

##### 📱 Platforms & Integrations

###### Heterogeneous Agents

- Claude Code supports local Provider bindings, while supported Claude Code and Codex runs can use deployment-backed models with operation-scoped authorization. (#18468, #18558, #18595, #18609, #18621)
- Kimi Code joins heterogeneous Agent provider bindings, and Pi gains a dedicated Desktop provider path. (#18720, #18721)
- Each Topic keeps its own heterogeneous model choice instead of rewriting the Agent default. (#18658)
- Cursor moves to a bidirectional ACP session with permis

_[Truncated at 4000 characters — full notes: https://github.com/lobehub/lobehub/releases/tag/v2.2.15]_