# lobehub v2.2.16 โ€” ๐Ÿš€ Release v2.2.16 - Product: lobehub (https://whatsnew.fyi/product/lobehub) - Vendor: lobehub - Date: 2026-09-04 - Version: v2.2.16 - Original notes: https://github.com/lobehub/lobehub/releases/tag/v2.2.16 - Permalink: https://whatsnew.fyi/product/lobehub/releases/v2.2.16 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 ยฉ What's New. Quote freely with attribution and a link back; wholesale republication of the corpus is not permitted โ€” terms: https://whatsnew.fyi/terms. The vendors' own release notes remain their publishers'. --- - **added** โ€” Factory Droid is available as a first-class ACP Agent with session resume, image input, cancellation, model configuration, and permission interventions - **added** โ€” Full-text search gains an Elasticsearch provider-neutral search layer with durable outbox, resumable indexing, operational recovery, and an opt-in Docker Compose profile - **added** โ€” CLI covers workspace selection, resilient Goal execution, operation inspection and replay, execution snapshots, and stronger daemon readiness checks - **added** โ€” Document comment threads gain participant notifications and deep links - **added** โ€” Shared documents can receive likes - **added** โ€” Tasks add assignments, mentions, and member-aware tool actions - **added** โ€” Direct Agent links provide a controlled visitor-chat surface with configurable grants, limits, and exposure settings - **added** โ€” Projects now host their own Acceptance workspace with scoped queries and contextual empty states - **added** โ€” Goal experience adds an exploration map, a detail portal, compact running-process controls, and a dedicated result-review view - **changed** โ€” Goal planning now records exploration structure, schedules independent Tasks in parallel, and bounds Goal reads, lifecycle transitions, and deadlines - **changed** โ€” Goal creation and execution stay non-blocking while the Goal page adds contextual chat, liveness heartbeats, and explicit process controls - **changed** โ€” TRAE supports provider binding through OpenAI Responses with isolated profiles and preserved authentication across model bindings - **changed** โ€” Deployment-provided LobeHub connection covers more local Agent drivers with operation-scoped credentials and capability checks including Grok Build support - **changed** โ€” Acceptance lists support pagination and batch actions with clearer reports, decisions, and evidence during review and reruns - **changed** โ€” Device clients time out black-holed handshakes, distinguish gateway read failures from an empty device list, and expose offline-device failures as recoverable states - **changed** โ€” Repeated tool loops are bounded and synthetic tool failures retain their reason and tool identity - **changed** โ€” Workspace browsing gains a more capable explorer with Agent Overview and Workspace separated more clearly - **changed** โ€” Large PDFs can be read without the earlier cap - **fixed** โ€” Agent Work verification no longer redispatches an already delivered Work item - **fixed** โ€” Network-success responses with empty completions can be retried safely ##### ๐Ÿ“ฆ Release v2.2.16 This release was automatically published from PR #19137. ###### Changes See PR description: https://github.com/lobehub/lobehub/pull/19137 ###### Commit Message #### ๐Ÿš€ LobeHub Release (v2.2.16) **Release Date:** September 3, 2026 **Since v2.2.15:** 246 merged PRs ยท 9 contributors > This release makes long-running Goals easier to plan, supervise, and accept; adds direct Agent sharing and a project-scoped Acceptance workspace; broadens local heterogeneous Agent support; and strengthens search, CLI, collaboration, performance, and gateway reliability. --- ##### โœจ Highlights - **More heterogeneous Agents, with safer bindings** โ€” Factory Droid joins through ACP, TRAE and Grok Build gain provider binding support, and the deployment-provided LobeHub connection expands across Claude Code, Codex, Kimi Code, Pi, and Grok Build. (#18737, #18775, #18785, #18811, #18932) - **Full-text search gains an Elasticsearch path** โ€” A provider-neutral search layer, durable outbox, resumable indexing, operational recovery, and an opt-in Docker Compose profile make Elasticsearch practical without changing the default self-hosted setup. (#18807, #18902, #19028) - **The CLI covers more of the Agent workflow** โ€” Workspace selection, resilient Goal execution, operation inspection and replay, execution snapshots, and stronger daemon readiness checks make `lh` more useful for repeatable local and remote workflows. (#18797, #18874, #19000, #19015, #19020) - **Workspace collaboration becomes more actionable** โ€” Document comment threads gain participant notifications and deep links, shared documents can receive likes, and Tasks add assignments, mentions, and member-aware tool actions. (#18750, #18999, #19035, #19039) - **Large workloads feel lighter** โ€” A CI-enforced first-screen graph cut, off-main-thread hashing, streaming upload paths, and larger PDF reads reduce startup and file-processing stalls. (#18945, #19033, #19065, #19073) - **Gateway and runtime failures recover more clearly** โ€” Device handshake deadlines, explicit device-read failures, recoverable offline-device states, bounded tool-loop handling, and synthetic tool-failure diagnosis prevent silent fallbacks and stuck execution. (#18965, #19021, #19022, #19069, #19116) --- ##### ๐Ÿ—๏ธ Core Agent & Architecture ###### Goals, Tasks & Acceptance - Goal planning now records exploration structure, schedules independent Tasks in parallel, and bounds Goal reads, lifecycle transitions, and deadlines. (#18942, #18944, #18970) - Goal creation and execution stay non-blocking, while the Goal page adds contextual chat, liveness heartbeats, explicit process controls, structured acceptance criteria, and a final result-review view. (#18979, #19050, #19124) - Acceptance lists support pagination and batch actions, and reports, decisions, and evidence are clearer during review and reruns. (#18843, #18844, #18896, #18897, #18901) - Projects now host their own Acceptance workspace, including scoped queries, contextual empty states, and a notice when a shared viewer cannot perform review actions. (#19042, #19064) ###### Runtime, Context & Agent Work - Agent Work verification no longer redispatches an already delivered Work item, and gateway tool-state updates are coalesced to reduce redundant traffic. (#18969, #19060) - Repeated tool loops are bounded, synthetic tool failures retain their reason and tool identity, and network-success responses with empty completions can be retried safely. (#18965, #19083, #19116) - Heterogeneous Agent lifecycle hooks persist across operations, while operation completion propagates through the hook chain. (#18408, #18946) - Agent documents keep their folder relationships, and workspace resource management is less restrictive where ownership and permissions already allow the operation. (#18964, #19107) --- ##### ๐Ÿ“ฑ Platforms & Integrations ###### Heterogeneous Agents - Factory Droid is available as a f _[Truncated at 4000 characters โ€” full notes: https://github.com/lobehub/lobehub/releases/tag/v2.2.16]_