* ✨ feat(agent-topics): add per-agent topic management page

Add /agent/:aid/topics — a dedicated management surface for browsing,
filtering, and bulk-operating on an agent's topics. Card grid view by
default with list view toggle, status / project / trigger / time filters,
keyword search, and multi-select bulk favorite / archive / delete.

A new "All Topics" entry in the agent sidebar (above the Topic accordion)
opens the page.

Frontend-only — no new TRPC procedures. Wires to the existing
useFetchTopics / useSearchTopics / favoriteTopic / updateTopicStatus /
removeTopic actions. Filters that the existing backend doesn't natively
support (project, time range, multi-sort) apply client-side on the loaded
page (default pageSize 100). Bulk favorite / archive loops single-action
calls; a proper batchUpdate procedure is left as a follow-up.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* 💄 style(agent-topics): UX iteration — sidebar entry, breadcrumb, byProject grouping, floating bulk bar

Major refinements after design review on PR lobehub#15207:

- Sidebar entry: moved from in-accordion to top nav between Profile and
  Channels, renamed "All Topics" → "Topics", uses MessagesSquare icon
- Header: breadcrumb (Agent / Topics) replaces standalone title; search
  bar moves into the NavHeader center slot; "New chat" + "Select" header
  buttons removed (selection enters via card hover-checkbox)
- Card refresh: compact layout (no fixed min-height, removed "No preview"
  fallback), favorite star moves to title prefix, hover reveals
  top-right checkbox, status renders as subtle StatusDot instead of
  saturated Tag, time uses platform `useActivityTime` (relative <24h,
  absolute date otherwise)
- Grouping: defaults to byTime; adds byProject + flat options matching
  the sidebar accordion modes; section titles in normal case
- Toolbar: status chips become a single Segmented control; Trigger
  dropdown items get icons (Chat/API/Scheduled/Eval); default trigger
  filter = ['chat'] so cron/api/eval noise hides by default
- List view: grid-template `minmax(0, 1fr)` + per-cell `min-width: 0`
  so long titles ellipsize instead of pushing other columns
- Layout: content max-width 1440, centered; grid `minmax(min(280px,
  100%), 1fr)` wraps cleanly when the agent sidebar expands
- Infinite scroll: IntersectionObserver sentinel + `loadMoreTopics`,
  PAGE_SIZE 30, shimmer text via `shinyTextStyles`
- BulkActionBar: floating pill at bottom-center (position: fixed,
  pointer-events isolated), ActionIcon buttons instead of full Buttons
- i18n: `management.*` namespace fleshed out across en/zh; zh "活跃"
  for active status (not "进行中")
- Backend: `topic.getTopics` SELECT now includes `description`;
  `ChatTopic` type adds `description?: string | null`

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* ✨ feat(agent-topics): bulk actions, stats columns, sticky header, list polish

Second iteration on PR lobehub#15207:

Backend (`topic.getTopics`)
- SELECT now returns `firstUserMessage` (correlated subquery, indexed via
  `messages_topic_id_idx`), `messageCount`, and `trigger`
- Mock `tokenUsage` / `cost` via `hashtext(topic.id)` so values are stable
  across refetches but look varied; will be replaced once real aggregation
  lands
- `ChatTopic` type adds matching optional fields

Page
- `ToolbarActions` (⋯ menu next to Sort): one-click "Archive topics
  inactive for 3+ months" (client-side iterate → `updateTopicStatus →
  completed`, with confirm and noneFound/done toasts), and an
  "Auto-generate summaries" entry stubbed to a Coming Soon toast until a
  topic-summary endpoint exists
- Status Segmented: drop `archived` and `favorite` (favorite isn't a
  status — keep the star indicator on the card/list instead); add
  `running` as its own slot
- `matchesTrigger` detects cron-spawned topics via `metadata.cronJobId`
  when `trigger` is null, so Daily Brief style data doesn't leak into the
  default Chat filter
- `clearFilters` resets to All instead of Active so users can confirm an
  empty result really is empty across the whole dataset
- Infinite-scroll: `IntersectionObserver` now uses the scroll container
  as `root` (was viewport — broken inside a nested scroller); sentinel +
  shimmer text rendered only when topics are actually present

Card
- Preview fallback chain `description → historySummary → firstUserMessage`
- Footer shows `messageCount` / `tokenUsage` (formatTokenNumber) / `cost`
  (formatPrice) alongside the activity time

List view
- Sticky header (`position: sticky; inset-block-start: 0`) with opaque
  `colorBgElevated` so scrolled rows don't bleed through
- "Select all" checkbox in header with indeterminate state; auto-enters
  selectMode on first activation
- Trigger column localized via `t('management.filters.trigger.*')`;
  Updated column right-aligned
- Grid template back to 6 columns (favorite star is now inline before
  the title)

Sidebar
- The Topic accordion's "Load more" entry (`FlatMode` + `GroupedAccordion`)
  now navigates to `/agent/:aid/topics` instead of opening the legacy
  `AllTopicsDrawer`

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* ✨ feat(agent-topics): infinite scroll, status counts, task trigger filter

- Per-agent paged fetch via new agentTopicsViewMap (action + selectors + initial state) with `withDetails` opt-in for card columns
- Toolbar status segmented control surfaces live counts; trigger filter switches `cron` → `task` (matches TaskRunnerService output) with ListTodo icon

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* ♻️ refactor(agent-topic-manager): rename folder, swap to LobeUI Checkbox

- Rename `AgentTopics` → `AgentTopicManager` (folder, displayNames, route import)
- Replace hand-rolled card checkbox with `@lobehub/ui` Checkbox (size 18, lighter border via colorBorder); list view also uses `@lobehub/ui` instead of antd
- Fix topic.query withDetails correlated subqueries: qualify column refs so `topic_id = topics.id` resolves correctly (drizzle `${table.col}` renders unqualified — previously matched against messages.id). Add covering tests.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* 🔧 chore(topic-query): drop mock cost/tokenUsage from withDetails, polish card

- topic.ts: stop emitting hashtext-mocked `cost` / `tokenUsage` in the
  `withDetails` branch — they need a real schema migration before they
  can be backed by actual numbers. Real aggregates (firstUserMessage,
  messageCount) and existing columns (description, trigger) still come
  back as before.
- Update test + JSDoc to match. The card already gracefully drops the
  cost row via `cost > 0` since the field is now undefined.
- TopicCard: drop the redundant `$` text before `formatPrice` — the
  CircleDollarSign icon already conveys the currency.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* 🙈 hide(agent-topic-manager): hide auto-summarize entry until migration lands

The auto-summarize menu item depends on the same schema migration that
gates cost / tokenUsage in the topic.query withDetails path. Drop it
from the ToolbarActions dropdown for now; i18n keys stay in place so
re-enabling is just adding the item back.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* ✅ test(agent-sidebar-nav): add MessagesSquareIcon to lucide-react mock

Nav.tsx now renders the agent-topic-manager entry via `MessagesSquareIcon`;
the test mock listed only the previous three icons, so the component
threw on render.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>

# 🚀 LobeHub Release (20260528)

**Release Date:** May 28, 2026  
**Since v2.2.0:** 220 merged PRs · 15 contributors

> This cycle brings heterogeneous "platform agents" you can dispatch to
local or remote devices, a rebuilt onboarding flow, document-centric
chat, and a unified model-runtime error model — with new DeepSeek V4 and
Gemini 3.5 Flash support along the way.

---

## ✨ Highlights

- **More Hetero Agents (OpenClaw / Hermes)** — Create heterogeneous
agents and dispatch them to local or remote devices through the device
gateway, with an execution-target switcher in the composer and
persistent CLI sessions. (#15065, #15179, #15022)
- **iMessage on Desktop** — New iMessage setup and bridge on desktop,
plus bot attachments across every platform. (#15228, #15227, #15029)
- **Skills in the Composer** — Drag skill chips into chat, trigger
installed skills from the slash menu mid-line, and surface project-level
skills in the homogeneous agent runtime. (#15095, #15061, #15110)
- **New Models** — DeepSeek V4 Flash/Pro and Gemini 3.5 Flash across
providers, with thinking params for structured output and chat cost
estimates. (#15031, #15001, #15051, #14876)
- **Agent Runtime Observability** — OpenTelemetry GenAI semantic
conventions plus per-call generation tracing. (#15123, #15124)

---

## 🤖 Agents & Heterogeneous Runtime

- **Platform agent creation** — OpenClaw/Hermes creation UI, device
guard, and remote dispatch backend. (#15065)
- **Execution-target switcher** — Pick local vs remote execution
directly in the composer; device-selection UX with actionable guidance.
(#15179, #15111)
- **CLI hetero dispatch** — OpenClaw/Hermes dispatch with persistent
sessions and a notify protocol. (#15022)
- **Gateway snapshot as source of truth** — Consume the gateway
`uiMessages` snapshot at step boundaries to keep chat state consistent.
(#15153, #15152)
- **Client sub-agent as a normal tool call** — Simplifies the sub-agent
execution path. (#15281)
- **Hermes agent chain** — Implements the Hermes agent chain logic.
(#15189)
- **Device registry** — TRPC endpoints to register, list, update, and
remove devices. (#15299)
- **Desktop device routing** — Route gateway agent runs through `lh
hetero exec`; restore `userId` in gateway dispatch and gate local-system
by execution target. (#15132, #15232)
- **Agent signals** — Anchor agent-signal receipts to messages and
isolate memory-agent messages into a child thread. (#14969, #14921)

---

## 🚀 Onboarding

- **Simplified first screen** — Defer topic creation to first send.
(#15090)
- **Market Agent Picker** — Added as a classic onboarding step, with
template prefetch. (#14980, #15041)
- **Welcome guidance** — Show agent welcome guidance on first run.
(#15098)
- **Mobile** — Adapt agent onboarding UI and restore Classic-step
padding on mobile. (#15019, #15032)
- **Discovery** — Streamline discovery to a single profession question.
(#14987)
- **Analytics** — Track onboarding step events and create-agent modal
source. (#15133, #15028)

---

## 📄 Documents, Pages & Knowledge

- **Thread chat in preview** — Embed thread chat in the document preview
portal. (#15216)
- **Non-markdown rendering** — Render non-markdown docs as a read-only
highlight. (#15272)
- **Multi-select** — Multi-select delete in the document tree. (#15125)
- **Page-agent streaming** — Preview `initPage` streaming arguments.
(#15039)
- **Per-agent topics** — Per-agent topic management page. (#15207)
- **Server-side category** — Derive document category server-side and
drop frontend predicates. (#15076)

---

## 🧩 Skills & Tools

- **Drag skill chips** — Drag skills into chat input and register
agent-document skills. (#15095)
- **Slash menu** — Installed skills appear in the slash menu with a
mid-line trigger. (#15061)
- **Project skills** — Recognize project-level skills in the homogeneous
agent runtime and surface them regardless of active device. (#15110,
#15177)
- **VFS archiving** — Archive oversized tool results to VFS instead of
truncating. (#15074)
- **@localfile mentions** — Drag folders into chat input as `@localFile`
mentions on desktop. (#15071)

---

## 🧠 Model Runtime & Providers

- **Error spec registry** — Unify error codes into a spec + pattern
registry, split `ProviderBizError` into finer codes, classify Cloud-only
codes via a tier digit, and add `DatabasePersistError`. (#15262, #15286,
#15278, #15279)
- **New models** — DeepSeek V4 Flash/Pro (opencode-go) and Gemini 3.5
Flash; DeepSeek V4 Pro on SiliconCloud. (#15031, #15001, #15017, #15267)
- **Structured output** — Thinking params for structured output, Bedrock
structured generation, and DeepSeek `generateObject` tool choice.
(#15051, #15174, #15054)
- **Cost** — Chat cost estimate support; preserve usage cost in custom
streams. (#14876, #15218)

---

## 💬 Chat & User Experience

- **Follow-up chips** — Extend follow-up chip suggestions to general
chat with scene-specific model config. (#15101, #14797)
- **Input drafts** — Persist unsent input drafts across tab switches and
prevent repeated draft restore. (#14992, #15024)
- **Command menu** — Order topic/message search by recency and promote
inline type filters. (#15094, #14986)
- **Zoom HUD** — Show a zoom-level HUD on Cmd +/− and Cmd 0. (#15294)
- **Copy** — Unescape markdown escapes when copying user messages.
(#15253)

---

## 🖥️ Desktop

- **App Nap fix** — Prevent App Nap from dropping the gateway WebSocket
during display sleep. (#14994)
- **File preview** — Preview `.cjs`/`.mjs`/no-extension files instead of
binary fallback and expand `~` when opening local files. (#15168,
#15284)
- **Cross-platform settings** — Open settings via main-window navigation
on Windows/Linux and restore the route after an update restart. (#15036,
#14922)
- **Token refresh** — Prevent frequent logout from token-refresh
retries. (#14928)

---

## 📊 Observability

- **OTel GenAI** — Instrument Agent Runtime with OpenTelemetry GenAI
semantic conventions. (#15123)
- **Generation tracing** — Per-call `llm_generation_tracing` with a
pre-allocated tracingId and recordFeedback router. (#15124, #15146)
- **Error classification** — Persist `ERROR_CODE_SPECS` classification
on operation errors. (#15273)

---

## 🗃️ Database Migrations

- **Batch migrations** — Topic usage stats, push tokens,
`tasks.editor_data`, and document shares. (#15280)
- **Tracing & eval tables** — Add `llm_generation_tracing` and agent
eval experiment tables. (#15126)

> Self-hosted operators should run the database migration (`pnpm
db:migrate`, or restart with auto-migrate enabled) after upgrading. The
changes are additive and backwards-compatible.

---

## 🔒 Security & Reliability

- **Security:** Remove the `getPlaintextCred` tool to prevent plaintext
credential exposure. (#14998)
- **Security:** Prompt account selection for Google OAuth and add
`prompt=consent` to the OIDC authorization URL to fix missing refresh
tokens. (#15234, #15010)
- **Reliability:** Preserve streamed content across a mid-stream cancel.
(#15173)
- **Reliability:** Bound the Redis command timeout and configure the
Anthropic client timeout. (#15091, #15042)
- **Reliability:** Prevent infinite recursion in the assistant chain.
(#15288)

---

## 👥 Contributors

Huge thanks to **15 contributors** who shipped **220 merged PRs** this
cycle.

@AnotiaWang · @sxjeru · @algojogacor · @hardy-one · @arvinxx · @Innei ·
@tjx666 · @lijian · @AmAzing129 · @rdmclin2 · @neko · @cy948 ·
@CanisMinor · @sudongyuer · @rivertwilight

Plus @lobehubbot and renovate[bot] for maintenance.

---

**Full Changelog**: v2.2.0...release/weekly-20260528