💄 style: polish onboarding interventions and add tool result renders#14506
Merged
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Codecov Report❌ Patch coverage is Additional details and impacted files@@ Coverage Diff @@
## canary #14506 +/- ##
=========================================
Coverage 68.90% 68.91%
=========================================
Files 2611 2611
Lines 228703 228746 +43
Branches 24161 28997 +4836
=========================================
+ Hits 157596 157631 +35
- Misses 70958 70966 +8
Partials 149 149
Flags with carried forward coverage won't be shown. Click here to find out more.
🚀 New features to boost your workflow:
|
The dev-mode actions pill at the bottom-right of the onboarding page covered the operation area below it. Add a chevron toggle so users can collapse the pill down to a single icon button. Collapsed state is persisted in localStorage so it survives reloads. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Lets the user override the agent's proposed identity in-place before
approving — pick a different emoji from the avatar picker, type into
the name field, and the edits flow through registerBeforeApprove ->
onArgsChange so the actual save uses the user's values.
Other changes:
- Title is now derived from the live edit state, so adding a missing
field flips the wording from "I'll update my name" to "I'll update my
name and avatar" without staleness
- Subtitle hint ("如果不满意，可以直接修改名字或头像") tells the user
the card is interactive
- Test covers the edit-flush path: edits to name + emoji are observed
via onArgsChange when the framework triggers the beforeApprove flush
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Drops the inline approve / reject button row in favor of a numbered two-option layout with a single Submit at the bottom-right, mirroring Codex's approval picker. The reject row's content is the reason input itself (placeholder doubles as the row label) so users can type a follow-up instruction in place; reason flows through to the existing rejectAndContinueToolCall(messageId, reason) action. Behavior: - Default selection is approve; arrow keys (↑/↓) and 1/2 switch options - Enter submits when no input is focused; reject input has its own Enter / ↑ handlers so typing doesn't hijack the picker - Window-level shortcuts skip while any input/textarea/contenteditable is focused, so the main chat composer is never affected - approvalMode='allow-list' adds a "Don't ask again for similar actions" checkbox under option 1, replacing the old split-button dropdown Also tighten the onboarding intervention editHint copy from "如果不满意，可以直接修改名字或头像" to "你可以直接在下方修改名字或头像" (positive framing instead of conditional). i18n changes (default + en-US + zh-CN): - Add optionApprove, rememberSimilar, submit - Repurpose rejectReasonPlaceholder as the inline reject row's placeholder - Drop now-unused approveAndRemember, approveOnce, rejectAndContinue, rejectTitle keys Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
ae174a0 to
1309e14
Compare
1309e14 to
1f106b8
Compare
- Move avatar and title into a single row (cardHeader) so the agent template title sits next to the avatar instead of below it; description stays as a multi-line block beneath - Switch card border from colorBorderSecondary to colorFillSecondary so the card outline is visible when sitting on the elevated picker panel - Mirror the row layout in the loading Skeleton so the shimmer matches Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
… submitAgentPick The marketplace tool was previously falling back to the generic raw-args "等 N 个参数" header. Add per-API Inspectors: - showAgentMarketplace: title + up to 3 localized category chips (sourced from existing CATEGORY_LABEL_I18N_KEYS in tool namespace); overflow shown as +N - submitAgentPick: title + selected agent count Wire AgentMarketplaceInspectors into builtin-tools/src/inspectors.ts under AgentMarketplaceManifest.identifier and export from the package's agentMarketplace/client surface. i18n adds (default + en-US + zh-CN tool namespace): - agentMarketplace.inspector.pickCount plurals - agentMarketplace.inspector.moreCategories plurals Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The agent narrates intent ("组建 Agent 团队" / "Assemble agent team")
rather than describing a UI surface ("打开助手市场" / "Open agent
marketplace"), which reads more naturally in the inspector header
during onboarding.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds a SubmitAgentPick Render that shows a grid of agent cards (avatar +
title + description + "already in library" tag) instead of the raw text
content the LLM consumes. Also wires the framework so custom-interaction
handlers can return structured pluginState alongside toolResultContent.
Framework changes:
- submitToolInteraction(options) now accepts a pluginState field. After
writing toolResultContent, the chat store calls
optimisticUpdatePluginState so the message's structured state is
available to render components (matching how server-executed builtin
tools persist state)
- Cloud-side wrapper in Conversation/store/slices/tool/action.ts
forwards the new field
- customInteractionHandlers.ts SubmitToolInteractionOptions adds
pluginState; handleAgentMarketplaceSubmit returns the install
summaries via pluginState (same shape that built the LLM-facing text)
Marketplace changes:
- InstallMarketplaceAgentSummary gains an avatar field; the install
helper threads marketAgent.avatar through
- New Render/SubmitAgentPick reads pluginState.summaries to draw a
responsive card grid (already-in-library entries dimmed + tagged)
- Wire AgentMarketplaceRenders through the package's
agentMarketplace/client surface and register under
AgentMarketplaceManifest.identifier in builtin-tools/src/renders.ts
Workflow display labels (collapsed grouped tool row):
- Add showAgentMarketplace ("Assembled agent team" / "组建了 Agent 团队")
and submitAgentPick ("Picked agents" / "选好了助手") to
TOOL_API_DISPLAY_NAMES so the collapsed group no longer falls back to
"Show Agent Marketplace" / "Submit Agent Pick" via toTitleCase
i18n adds (default + en-US + zh-CN):
- tool.agentMarketplace.render.alreadyInLibrary plurals + alreadyInLibraryTag
- chat.workflow.toolDisplayName.{showAgentMarketplace,submitAgentPick}
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Replace the raw "Updated persona document (id). Applied N hunk(s)."
text with a structured per-hunk diff view rendered from args.hunks
(no executor state changes — args already carry the patches).
For each hunk render a mode label + line range chip and paint the
affected text:
- replace: removed (red border) → added (green border)
- delete: removed only
- insertAt: green block + L<line> chip
- replaceLines: green block + line range chip
- deleteLines: line range chip only (no body)
The total hunk count piggy-backs on the first hunk's label row instead
of getting its own header (the inspector header chip already shows
total + doc type, so a separate render-side header would be redundant).
i18n adds builtins.lobe-web-onboarding.updateDocument.hunkMode.{replace,
delete,deleteLines,insertAt,replaceLines} across default + en-US +
zh-CN.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Merged
Innei
added a commit
that referenced
this pull request
May 9, 2026
# 🚀 LobeHub Release (20260509) **Release Date:** May 9, 2026 **Since v2.1.56:** 236 merged PRs · 19 contributors > Agent Task System reaches general availability, the Agent Signal pipeline runs nightly self-review with skill-aware policies, the heterogeneous-agent runtime crosses replica boundaries, inline documents become a first-class context source, and bot platforms expand across Messager, Line, and Telegram. --- ## ✨ Highlights - **Agent Task System (GA)** — End-to-end task execution platform: templates, tracking, comment tools, parent reassignment, scheduled cron, and dependency-ordered batch runs. (#14540, #14515, #14517, #14272, #14246, #14418, #14403, #14488) - **Agent Signal nightly self-review** — Wired self-review loop with prompt + DB support, exponential-backoff retry on receipt listing, skill-aware policy, and improved skill-intent detection. (#14543, #14542, #14281, #14409, #14526, #14437) - **Inline documents in KB tool** — BM25 search and `docs_*` read for inline document grounding; agent documents usable as VFS. (#14494, #14222) - **Inline agent cards in chat** — `lobeAgents` markdown tag renders agent profile cards inline; clickable card after `createAgent`. (#14495, #14493) - **Heterogeneous agent runtime** — Cloud hetero exec pipeline steps 3+4 land, persistence recovers across Vercel replicas, server-side ingest/finish handler, and `lh hetero exec` CLI. (#14486, #14539, #14444, #14431) - **Bot platforms expand** — Messager, Line, DM pair policy, and messenger DB tables; Telegram API path restored. (#14442, #14207, #14211, #14496, #14519) - **Visual analysis tool** — New visual understanding tool, with trigger tracking and flattened schema. (#14378, #14399, #14550) - **DeepSeek V4 Pro as OSS default** — OSS deployments ship with DeepSeek V4 Pro by default; DeepSeek Anthropic runtime supported. (#14555, #14312) --- ## 🏗️ Core Agent & Architecture ### Agent Task System - **Task System GA** — End-to-end execution platform now available. (#14540) - **Templates, comments, reparenting** — Template tracking, comment tools, and parent reassignment. (#14515, #14517, #14488) - **Cron + dependency-ordered runs** — Scheduled status with cron editor and dependency-ordered subtask batches. (#14246, #14418, #14272) - **Inspector + chip UI + batch tasks** — Task Inspector/Render registry, batch `createTasks`/`runTasks`, and chip-based agent-documents inspector. (#14403, #14404) - **Recommend templates regardless of brief count** — Recommendations no longer suppressed when briefs are sparse. (#14508) - **Scheduling resilience** — Manual run no longer eats next scheduled tick; recurring tasks survive brief resolution. (#14304, #14348) - **Brief synthesis** — Auto-synthesize topic briefs; brief actions revamp; mute resolved-brief icon on home. (#14324, #14228, #14452) - **Task list & detail polish** — Topic operation ID exposed; task drawer Gateway reconnect. (#14282) ### Agent Signal pipeline - **Nightly self-review wired** — Prompt + DB support for the self-review loop. (#14543) - **Self-review activities push to briefs** — Activities during nightly self-reflection now create briefs. (#14437) - **Skill management policy** — New policy for Skill management running inside Agent Signal. (#14281) - **Skill intent detection & routing** — Improved detection plus direct intent handling when `hintIsSkill`. (#14409, #14526) - **Document tool outcome rendering** — Decision view restores missing document tool outcomes. (#14534) - **Exponential backoff retry** — Listing signal receipts retries with jittered backoff. (#14542) - **Easier-to-use signals** — Structural simplification + recent-activities surface for receipts. (#14290, #14326, #14407) ### Heterogeneous agent runtime - **Cloud hetero exec pipeline (steps 3 + 4)** — Refactor lands the next two stages of the cloud hetero agent execution pipeline. (#14486) - **Persistence recovery on Vercel** — Hetero state recovered across replica boundaries. (#14539) - **Server-side ingest/finish + persistence** — `aiAgent.heteroIngest` / `heteroFinish` handlers. (#14444) - **`lh hetero exec` CLI** — Standalone heterogeneous agent runs from CLI. (#14431) - **Gateway round-trip loading** — `execAgentTask` keeps the input box in loading state through the full round-trip. (#14503) - **Provider SDK type routing** — Provider routing now respects SDK type. (#14520) - **DeepSeek reasoning preserved** — `reasoning_content` preserved in OpenAI-compatible runtime for DeepSeek models. (#14546) ### Knowledge & inline docs - **KB tool BM25 + docs read** — BM25 search and `docs_*` read integrated for inline documents. (#14494) - **Agent documents as VFS** — FS-compatible output for agent documents. (#14222) - **`lobeAgents` markdown tag** — Inline agent cards rendered from a markdown tag. (#14495) - **Clickable agent card after `createAgent`** — Mentions and recommendations become clickable. (#14493) - **ExplorerTree** — Generic tree component built on `@pierre/trees` for reusable explorer surfaces. (#14094) - **Local file mention snapshots** — Mentions can now snapshot local files. (#14278) ### Architecture - **Agent Hono routes** — New agent routes added on Hono. (#14535) - **`/api/agent` migrated to Hono** — Remaining `/api/agent` routes finish their migration. (#14478) - **Agent marketplace merged into web-onboarding** — Reduces package fragmentation. (#14514) - **Producer pipeline extracted** — Shared package for the producer pipeline. (#14425) - **`agentDispatcher.selectRuntimeType`** — New runtime selection abstraction. (#14428) - **pnpm v11 migration** — Workspace consolidated. (#14316) - **Browser-compatible frontmatter parser** — Replaces `gray-matter`. (#14435) --- ## 📱 Platforms & Integrations - **Messager support** — New messager package wired into the chat surface. (#14442) - **Messenger DB tables** — IM bot integration gains its persistence layer. (#14496) - **Line bot** — Initial Line support and downstream optimization. (#14207, #14448) - **DM pair policy** — Group/DM pair-based delivery. (#14211) - **Telegram API restored** — Missing Telegram API path reconnected. (#14519) - **xAI Responses tools stabilized** — Plus unsupported parameter handling. (#14462, #14445) - **Volcengine websearch via ResponseAPI** — Built-in websearch for Volcengine. (#14216) --- ## 🤖 Models & Providers - **DeepSeek V4 Pro default for OSS** — OSS distribution defaults to DeepSeek V4 Pro. (#14555) - **DeepSeek Anthropic runtime** — Anthropic-shape runtime support for DeepSeek. (#14312) - **GPT-5.5 / GPT-5.5 Pro** — New OpenAI tier. (#14142) - **Grok 4.20 / Grok 4.3 / LobeHub-hosted Grok 4.3** — (#14253, #14382, #14446) - **Gemma 4 + provider settings normalization** — (#13313) - **gpt-image-2 + step-image-edit-2** — (#14253, #14329) - **Model bank refresh + original-pricing display** — Batch model updates and pricing surfaces. (#14070, #14391) - **Hunyuan migrated to TokenHub for Hy3 Preview** — (#14108) - **Reject lobehub model ids no longer in the bank** — (#14261) - **Hide runtime-only aliases** — Runtime-only model aliases no longer leak into the model picker. (#14552) --- ## 🖥️ User Experience ### Onboarding - **Shared prefix steps** — Language and privacy extracted as shared prefix steps. (#14538) - **Identity intervention card simplified** — Plus tool result renders cleanup. (#14505, #14506) - **Welcome polish + web-onboarding tool UI** — (#14475) - **Templates fetched from market API** — (#14286) - **Virtual model id for default onboarding model** — (#14311) - **Skip / mode-switch footer behind feature flag** — Footer guarded for desktop and web initialization. (#14560) ### Home & navigation - **Home recents performance** — Recents refresh periodically and inline task status; brief and task-template fetch overhead trimmed. (#14518, #14516) - **Home refactor + skill-connect recommendations** — Restructured home with skill-connect recommendation system. (#14266, #14214) - **Tasks in agent sidebar** — Tasks moved from welcome card into the sidebar list. (#14500) - **Sidebar collapse persists** — Home sidebar collapse state stored. (#14473) - **Agent-specific topic grouping** — Plus improved empty state and agent identity in topic search. (#14225) - **MentionMenu scroll fix** — Mention menu no longer clips inside chat input. (#14533) ### Conversation & chat - **Follow-up chips fill input** — Clicking a follow-up chip now fills the input instead of sending immediately. (#14536) - **Quick-reply chips below assistant messages** — (#14350) - **Inline single-tool assistant group + leading sentence promotion** — (#14244) - **Assistant-group rendering** — Per-segment content overrides flow into MessageContent. (#14504) - **Tool call timer fix** — Timer no longer resets when tool calls collapse or expand. (#14513) - **Streaming re-render reduction** — Reference stabilization and self-subscribing components. (#14470) - **Topic chat drawer feedback input** — (#14392) ### Skills, agents, devtools - **Managed skill folders** — Agent view displays managed skill folders and aligns delete confirmations. (#14553) - **Review tab + bulk git diffs** — New Review tab with bulk diffs; gating uses effective working directory. (#14334, #14512) - **Devtools gallery rebuild** — Plus Review polish, queue-tray images. (#14423) - **Agent mock devtools** — Playback & fixture viewer. (#14436) ### Desktop & CLI - **App tray visibility setting** — (#14463) - **Notification settings in desktop** — (#14491) - **Multimodal input across CLI / shared spawn / desktop** — (#14433) - **CLI bot + userId guide** — (#14258) --- ## 🔧 Tooling - **Visual analysis tool** — New visual understanding tool with flattened schema. (#14378, #14550) - **GitHub marketplace tool UI** — (#14420) - **Drop "Local" prefix and `____builtin` suffix from tool names** — (#14364, #14289) - **Sanitize provider tool names** — Avoids invalid characters from external providers. (#14510) - **Generation moderation context** — Moderation context passed through the generation pipeline. (#14541) - **Visual analysis trigger tracking** — (#14399) - **Claude thinking signature sanitization** — History signatures sanitized when replaying Claude conversations. (#14499) - **Responses input media sanitization** — Assistant media sanitized in Responses input. (#14497) --- ## 🔒 Security & Reliability - **Security:** Removed the `/webapi/proxy` route and dead URL-manifest plugin code to shrink the SSRF surface. (#14549) - **Security:** Sessions revoked after password reset. (#14424) - **Reliability:** Added `prompt_cache_key` to OpenAI chat requests for stable cache hits. (#14349) - **Reliability:** `onFinish` now fires even when the browser tab is backgrounded mid-SSE stream. (#14461) - **Reliability:** Better-auth session refetch preserves user fields rather than overwriting them. (#14531) - **Reliability:** User-memory queries sanitize backticks; user-memory errors now explicitly injected so failures stay visible. (#14524, #14525) - **Reliability:** Auth captcha retries handled; input loading unsticks on `auth_failed` and recoverable `auth_expired`. (#14346, #14419) - **Reliability:** Trace snapshot finalized on error path. (#14440) - **Reliability:** Drop `switchTopic` race under rapid sidebar clicks. (#14115) - **Reliability:** PDF chunking logic fixed to prevent vectorization failure. (#14327) - **Performance:** Marketplace fork uses a batched API for parallel installs. (#14537) - **Performance:** Review tab open latency cut ~9× on large dirty trees. (#14338) --- ## 👥 Contributors Huge thanks to **18 contributors** who shipped **236 merged PRs** this cycle. @hezhijie0327 · @sxjeru · @yueyinqiu · @octo-patch · @hardy-one · @Coooolfan · @CanYuanA · @BillionClaw · @arvinxx · @tjx666 · @Innei · @neko · @AmAzing129 · @rdmclin2 · @lijian · @sudongyuer · @rivertwilight · @cy948 Plus @lobehubbot for i18n and translation maintenance. --- **Full Changelog**: v2.1.56...release/weekly-20260509
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
💻 Change Type
🔗 Related Issue
N/A — broad UX polish pass on the onboarding flow's tool surfaces.
🔀 Description of Change
A grab-bag of onboarding polish on top of #14505's intervention card baseline. All framework-level pieces are scoped to make the existing surfaces nicer to look at and use; behavior of the underlying tools is unchanged.
Approval picker redesign (framework-wide)
ApprovalActions.tsxswaps the inline approve/reject button row for a numbered two-option picker with a single Submit at the bottom-right (Codex-style). Option ② "拒绝，并告诉 Agent 接下来该怎么做" turns the row content itself into a single-line input — placeholder doubles as the row label,Entersubmits the rejection with reason,↑moves back to ①. Window-level1/2/↑/↓/Entershortcuts work when no input is focused; the chat composer is never hijacked.approvalMode='allow-list'adds a small☐ 类似操作不再询问checkbox under option ① — clean replacement for the previous split-button dropdown.SaveUserQuestion intervention card
registerBeforeApprove→onArgsChangeso the actual save uses the user's valuesAgent marketplace tool surface
showAgentMarketplace(title + up to 3 localized category chips, +N for overflow) andsubmitAgentPick(count meta)submitAgentPickshowing a responsive grid of agent cards (avatar + title + description; already-in-library entries dimmed + tagged). Powered by a tiny framework extension:submitToolInteraction(options)now accepts apluginStatefield so custom-interaction handlers can persist structured state alongsidetoolResultContentInstallMarketplaceAgentSummarycarriesavatarso the Render has full visual fidelitycolorFillSecondaryso it stays visible on the elevated picker panelshowAgentMarketplaceapiName label from "Open agent marketplace" → "Assemble agent team" / "组建 Agent 团队" so it reads as agent intent, not a UI verb. Same label registered underTOOL_API_DISPLAY_NAMES(past-tense for the collapsed tool group row)UpdateDocument Render
builtin-tool-web-onboardingadds a Render forupdateDocument. The Render readsargs.hunks(no executor changes) and lays out each hunk as a per-mode block: replace renders red-barsearchfollowed by green-barreplace; delete is red-barsearchonly; insertAt / replaceLines render green-barcontentwith a line-range chip; deleteLines is just the chip. Total hunk count piggy-backs on the first hunk's label row instead of a separate header (the inspector chip already shows it).Misc
webOnboarding.test.tsxcovers the editable name+emoji flush path and the field-aware title branches🧪 How to Test
bun run type-checkpasseswebOnboarding.test.tsxpasses (5 cases)Onboarding flow: pick an agent name, switch emoji, approve → name+avatar applied; reject with reason → reason flows back to chat
Marketplace pick: pick 2–3 agents → submit → cards render with avatars and titles; already-installed ones show dimmed
Document update: invoke
updateDocumentwith mixed-mode hunks → diff blocks render correctly per modeTested locally
Added/updated tests
No tests needed
📸 Screenshots / Videos
🤖 Generated with Claude Code