β¨ feat(task-template): add home recommendation system with skill connect#14214
Merged
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Codecov Reportβ Patch coverage is Additional details and impacted files@@ Coverage Diff @@
## canary #14214 +/- ##
==========================================
- Coverage 68.13% 68.09% -0.04%
==========================================
Files 2271 2275 +4
Lines 194844 195247 +403
Branches 23587 19678 -3909
==========================================
+ Hits 132749 132956 +207
- Misses 61964 62159 +195
- Partials 131 132 +1
Flags with carried forward coverage won't be shown. Click here to find out more.
π New features to boost your workflow:
|
There was a problem hiding this comment.
π‘ Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 3087f26ad1
βΉοΈ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with π.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| const taskTemplateProcedure = authedProcedure.use(serverDatabase); | ||
|
|
||
| const listDailyRecommendSchema = z.object({ | ||
| interestKeys: z.array(z.string().max(64)).max(32), |
There was a problem hiding this comment.
Accept longer interest strings in recommendation input
This schema now rejects any interestKeys entry longer than 64 chars, but onboarding currently allows arbitrary custom interest text and useResolvedInterestKeys forwards it unchanged. For users who entered a long custom interest, listDailyRecommend will fail validation and the recommendation section silently disappears instead of falling back to generic templates.
Useful? React with πΒ / π.
8da0829 to
3818995
Compare
Render 3 schedule-task template cards in Home Daily briefs section when the user has β€1 unresolved brief. Tapping a card creates an agentCronJob via the inbox agent. Picks are interest-matched against INTEREST_AREAS keys with fallback to generic categories; seeded shuffle keeps results stable per (userId, utcDate). Client resolves localized `user.interests` labels back to canonical keys via the current-locale onboarding translations before calling the server β the server takes `interestKeys` as tRPC input rather than querying the DB, so it works cleanly with both old label-form data and freeform custom text (latter falls through to fallback pool).
β¦section Hide DailyBrief GroupBlock when there are no briefs to show, and mount TemplateRecommendations as an independent section on the home page with its own Lightbulb + title header, matching the Try these examples layout.
Drop the custom createFromTemplate mutation and call the shared agentCronJobService.create from the frontend, using builtinAgentSelectors to resolve the inbox agent id. The server BriefTemplateService now only handles listDailyRecommend and no longer needs a database handle.
Align code identifiers, file names, locale namespaces and tRPC router with the product term "Schedule Task Template". - briefTemplate β taskTemplate (files, types, services, router, i18n ns) - BriefTemplate β TaskTemplate - BRIEF_TEMPLATE_FALLBACK_CATEGORIES β TASK_TEMPLATE_FALLBACK_CATEGORIES
Move TemplateRecommendations out of features/DailyBrief into a sibling features/TaskTemplates folder. Split the shared style.ts so the new feature owns its own card and iconBadge styles. - features/TaskTemplates/index.tsx (component renamed to TaskTemplates) - features/TaskTemplates/style.ts (own card + iconBadge) - features/DailyBrief/style.ts drops recommendStyles - routes/(main)/home/features/index.tsx imports the new path
Add user_task_template_interactions table with firstCreatedAt/dismissedAt nullable timestamps to support sticky exclusion of created templates and dismissed cards from daily recommendations. This is the persistence base for LOBE-8186 (exclude created) and LOBE-8187 (dismiss card); router/UI integration lands in those follow-ups.
β¦ecommendations - agentCronJob.create accepts optional templateId and writes interaction - listDailyRecommend filters out templates the user has interacted with - TaskTemplateCard passes template.id when creating a cron job
- Rename "tasks" β "scheduled tasks" in section title and CTA - Point success toast to Lobe AI (where schedule tasks actually live) instead of the non-existent /tasks page
- taskTemplate.dismiss tRPC mutation backed by UserTaskTemplateInteractionModel - TaskTemplateCard hover-fade Γ button with optimistic SWR removal, reverts via revalidate on failure - Fix agentCronJobService.create signature to include optional templateId (was sending it at runtime since db139f4 but not typed)
Move parseCronPattern, buildCronPattern, ScheduleType from the route-local CronConfig.ts into the shared @lobechat/utils package, alongside new formatScheduleTime and WEEKDAY_I18N_KEYS helpers. Update existing callers in cron/[cronId] to import from the new location. Add unit tests covering daily / weekly / hourly forms, minute normalization, and buildCronPattern round-trips.
β¦BE-8191) Render the cron-derived schedule time (e.g. "Every day at 09:00", "Every Monday at 09:00") below each template description so users can see the cadence before adding it as a scheduled task. Reuse the shared parseCronPattern from @lobechat/utils/cron and the existing setting:agentCronJobs.weekday.* keys for weekday names.
β¦d templates (LOBE-8188) Add `requiresSkills` field to TaskTemplate so recommendation cards can route unconnected providers through the existing LobeHub Skill / Klavis OAuth flows before the user creates a cron job. Server filters out templates whose required skill sources are disabled by env so users never see Connect buttons that can't complete. - introduce `useSkillConnection` facade hook unifying both providers (postMessage + window monitor + 1s polling, 15s timeout) - ship 3 PoC templates: github-pr-review-daily, notion-weekly-digest, weekly-engineering-digest (multi-skill)
Add optional `icon` field on TaskTemplate so individual templates can ship a more recognizable Lucide glyph (Github / Radar / Type / GitPullRequest / etc). Cards fall back to the category-level default when unset.
- correct taskTemplates count assertion (16 β 19; was failing CI) - use browser timezone instead of hardcoded UTC for cron creation - useSkillConnection: useRef sync lock prevents double-open OAuth popups - useSkillConnection: 5min overall timeout on the popup window monitor - useSkillConnection: validate event.source on postMessage handler - useSkillConnection: drop expected-failure log noise from fallback polling - cron: extract SCHEDULE_MINUTE_STEP / ALL_WEEKDAYS / normalizeMinuteToHalfHour - separate type imports in 5 files (project typescript skill convention) - ICON_BY_CATEGORY: drop unnecessary quotes for plain identifiers - DailyBrief: collapse three conditional returns into one - TaskTemplates: rename filter param (t) β (tmpl) to avoid shadowing i18n t - locales: order resources alphabetically + section.title above templates
lucide-react@1.11.0 dropped brand icons. Use SiGithub from @icons-pack/react-simple-icons (already a dep, used elsewhere) and widen TaskTemplate.icon to LucideIcon | IconType so future templates can pick from either set.
β¦ent slot - Drop user_task_template_interactions table, model, migration, and lambda router - Replace src/features/TaskTemplates with an empty client business slot (src/business/client/RecommendTaskTemplates.tsx β memo(() => null)) - Stop persisting templateId in agentCronJob.create; cloud handles it via its own dedicated trpc namespace - Keep the catalog (@lobechat/const), TaskTemplateService (pure algorithm), and taskTemplate i18n keys β all reused by the cloud override
Update brief catalog and onboarding interests per LOBE-8033 product spec. - TaskTemplateCategory: add 9 new categories (sales-customer, operations, hr, finance-legal, creator, investing, parenting, health, hobbies) - taskTemplates: replace 19 placeholder samples with 80 production briefs covering all 17 categories, gated to clean daily/weekly cron schedules - INTEREST_AREAS: add 9 matching interests with lucide icons - i18n: rewrite default (en) + zh-CN (preview) for all 80 brief titles, descriptions, and prompts; expand onboarding interest labels - tests: bump length assertion to 80, expand interest whitelist to 17, add scheduleType guard so future monthly/event-driven cron entries fail loudly instead of silently rendering as daily Out of scope (follow-up issues): - monthly/quarterly/event-driven schedule support - optionalSkills + OR-relation skill data structures - Mailchimp / Apple Health / Google Fit provider registration
β¦chment Introduces `optionalSkills` on `TaskTemplate` so briefs that benefit from a connected skill but can run without one stop being filtered out of the catalog. Adds 4 new briefs (content-calendar-weekly, family-task-schedule, morning-ritual, bedtime-gratitude) covering the LOBE-8033 designs that were previously dropped because of the OR/optional skill semantics, plus a new `action.optionalConnect.button` CTA copy for the UI hint.
02e87c7 to
f719eb6
Compare
- Tolerate multi-space cron strings via split(/\s+/) and trim - Add explicit radix=10 to all parseInt calls - Avoid mutating input weekdays via copy + numeric sort
Move taskTemplate from a dedicated tRPC namespace into the standard business slot pattern (alongside subscription, topUp, referral, etc.) so cloud overrides can plug a real router into the lambda router and reuse the shared client/context infrastructure.
sxueck
pushed a commit
to sxueck/lobehub
that referenced
this pull request
Apr 28, 2026
mutoe
pushed a commit
to mutoe/lobehub
that referenced
this pull request
May 1, 2026
Innei
added a commit
that referenced
this pull request
May 9, 2026
# π LobeHub Release (20260509) **Release Date:** May 9, 2026 **Since v2.1.56:** 236 merged PRs Β· 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. --- ## β¨ Highlights - **Agent Task System (GA)** β 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** β 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** β BM25 search and `docs_*` read for inline document grounding; agent documents usable as VFS. (#14494, #14222) - **Inline agent cards in chat** β `lobeAgents` markdown tag renders agent profile cards inline; clickable card after `createAgent`. (#14495, #14493) - **Heterogeneous agent runtime** β 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** β Messager, Line, DM pair policy, and messenger DB tables; Telegram API path restored. (#14442, #14207, #14211, #14496, #14519) - **Visual analysis tool** β New visual understanding tool, with trigger tracking and flattened schema. (#14378, #14399, #14550) - **DeepSeek V4 Pro as OSS default** β OSS deployments ship with DeepSeek V4 Pro by default; DeepSeek Anthropic runtime supported. (#14555, #14312) --- ## ποΈ Core Agent & Architecture ### Agent Task System - **Task System GA** β End-to-end execution platform now available. (#14540) - **Templates, comments, reparenting** β Template tracking, comment tools, and parent reassignment. (#14515, #14517, #14488) - **Cron + dependency-ordered runs** β Scheduled status with cron editor and dependency-ordered subtask batches. (#14246, #14418, #14272) - **Inspector + chip UI + batch tasks** β Task Inspector/Render registry, batch `createTasks`/`runTasks`, and chip-based agent-documents inspector. (#14403, #14404) - **Recommend templates regardless of brief count** β Recommendations no longer suppressed when briefs are sparse. (#14508) - **Scheduling resilience** β Manual run no longer eats next scheduled tick; recurring tasks survive brief resolution. (#14304, #14348) - **Brief synthesis** β Auto-synthesize topic briefs; brief actions revamp; mute resolved-brief icon on home. (#14324, #14228, #14452) - **Task list & detail polish** β Topic operation ID exposed; task drawer Gateway reconnect. (#14282) ### Agent Signal pipeline - **Nightly self-review wired** β Prompt + DB support for the self-review loop. (#14543) - **Self-review activities push to briefs** β Activities during nightly self-reflection now create briefs. (#14437) - **Skill management policy** β New policy for Skill management running inside Agent Signal. (#14281) - **Skill intent detection & routing** β Improved detection plus direct intent handling when `hintIsSkill`. (#14409, #14526) - **Document tool outcome rendering** β Decision view restores missing document tool outcomes. (#14534) - **Exponential backoff retry** β Listing signal receipts retries with jittered backoff. (#14542) - **Easier-to-use signals** β Structural simplification + recent-activities surface for receipts. (#14290, #14326, #14407) ### Heterogeneous agent runtime - **Cloud hetero exec pipeline (steps 3 + 4)** β Refactor lands the next two stages of the cloud hetero agent execution pipeline. (#14486) - **Persistence recovery on Vercel** β Hetero state recovered across replica boundaries. (#14539) - **Server-side ingest/finish + persistence** β `aiAgent.heteroIngest` / `heteroFinish` handlers. (#14444) - **`lh hetero exec` CLI** β Standalone heterogeneous agent runs from CLI. (#14431) - **Gateway round-trip loading** β `execAgentTask` keeps the input box in loading state through the full round-trip. (#14503) - **Provider SDK type routing** β Provider routing now respects SDK type. (#14520) - **DeepSeek reasoning preserved** β `reasoning_content` preserved in OpenAI-compatible runtime for DeepSeek models. (#14546) ### Knowledge & inline docs - **KB tool BM25 + docs read** β BM25 search and `docs_*` read integrated for inline documents. (#14494) - **Agent documents as VFS** β FS-compatible output for agent documents. (#14222) - **`lobeAgents` markdown tag** β Inline agent cards rendered from a markdown tag. (#14495) - **Clickable agent card after `createAgent`** β Mentions and recommendations become clickable. (#14493) - **ExplorerTree** β Generic tree component built on `@pierre/trees` for reusable explorer surfaces. (#14094) - **Local file mention snapshots** β Mentions can now snapshot local files. (#14278) ### Architecture - **Agent Hono routes** β New agent routes added on Hono. (#14535) - **`/api/agent` migrated to Hono** β Remaining `/api/agent` routes finish their migration. (#14478) - **Agent marketplace merged into web-onboarding** β Reduces package fragmentation. (#14514) - **Producer pipeline extracted** β Shared package for the producer pipeline. (#14425) - **`agentDispatcher.selectRuntimeType`** β New runtime selection abstraction. (#14428) - **pnpm v11 migration** β Workspace consolidated. (#14316) - **Browser-compatible frontmatter parser** β Replaces `gray-matter`. (#14435) --- ## π± Platforms & Integrations - **Messager support** β New messager package wired into the chat surface. (#14442) - **Messenger DB tables** β IM bot integration gains its persistence layer. (#14496) - **Line bot** β Initial Line support and downstream optimization. (#14207, #14448) - **DM pair policy** β Group/DM pair-based delivery. (#14211) - **Telegram API restored** β Missing Telegram API path reconnected. (#14519) - **xAI Responses tools stabilized** β Plus unsupported parameter handling. (#14462, #14445) - **Volcengine websearch via ResponseAPI** β Built-in websearch for Volcengine. (#14216) --- ## π€ Models & Providers - **DeepSeek V4 Pro default for OSS** β OSS distribution defaults to DeepSeek V4 Pro. (#14555) - **DeepSeek Anthropic runtime** β Anthropic-shape runtime support for DeepSeek. (#14312) - **GPT-5.5 / GPT-5.5 Pro** β New OpenAI tier. (#14142) - **Grok 4.20 / Grok 4.3 / LobeHub-hosted Grok 4.3** β (#14253, #14382, #14446) - **Gemma 4 + provider settings normalization** β (#13313) - **gpt-image-2 + step-image-edit-2** β (#14253, #14329) - **Model bank refresh + original-pricing display** β Batch model updates and pricing surfaces. (#14070, #14391) - **Hunyuan migrated to TokenHub for Hy3 Preview** β (#14108) - **Reject lobehub model ids no longer in the bank** β (#14261) - **Hide runtime-only aliases** β Runtime-only model aliases no longer leak into the model picker. (#14552) --- ## π₯οΈ User Experience ### Onboarding - **Shared prefix steps** β Language and privacy extracted as shared prefix steps. (#14538) - **Identity intervention card simplified** β Plus tool result renders cleanup. (#14505, #14506) - **Welcome polish + web-onboarding tool UI** β (#14475) - **Templates fetched from market API** β (#14286) - **Virtual model id for default onboarding model** β (#14311) - **Skip / mode-switch footer behind feature flag** β Footer guarded for desktop and web initialization. (#14560) ### Home & navigation - **Home recents performance** β Recents refresh periodically and inline task status; brief and task-template fetch overhead trimmed. (#14518, #14516) - **Home refactor + skill-connect recommendations** β Restructured home with skill-connect recommendation system. (#14266, #14214) - **Tasks in agent sidebar** β Tasks moved from welcome card into the sidebar list. (#14500) - **Sidebar collapse persists** β Home sidebar collapse state stored. (#14473) - **Agent-specific topic grouping** β Plus improved empty state and agent identity in topic search. (#14225) - **MentionMenu scroll fix** β Mention menu no longer clips inside chat input. (#14533) ### Conversation & chat - **Follow-up chips fill input** β Clicking a follow-up chip now fills the input instead of sending immediately. (#14536) - **Quick-reply chips below assistant messages** β (#14350) - **Inline single-tool assistant group + leading sentence promotion** β (#14244) - **Assistant-group rendering** β Per-segment content overrides flow into MessageContent. (#14504) - **Tool call timer fix** β Timer no longer resets when tool calls collapse or expand. (#14513) - **Streaming re-render reduction** β Reference stabilization and self-subscribing components. (#14470) - **Topic chat drawer feedback input** β (#14392) ### Skills, agents, devtools - **Managed skill folders** β Agent view displays managed skill folders and aligns delete confirmations. (#14553) - **Review tab + bulk git diffs** β New Review tab with bulk diffs; gating uses effective working directory. (#14334, #14512) - **Devtools gallery rebuild** β Plus Review polish, queue-tray images. (#14423) - **Agent mock devtools** β Playback & fixture viewer. (#14436) ### Desktop & CLI - **App tray visibility setting** β (#14463) - **Notification settings in desktop** β (#14491) - **Multimodal input across CLI / shared spawn / desktop** β (#14433) - **CLI bot + userId guide** β (#14258) --- ## π§ Tooling - **Visual analysis tool** β New visual understanding tool with flattened schema. (#14378, #14550) - **GitHub marketplace tool UI** β (#14420) - **Drop "Local" prefix and `____builtin` suffix from tool names** β (#14364, #14289) - **Sanitize provider tool names** β Avoids invalid characters from external providers. (#14510) - **Generation moderation context** β Moderation context passed through the generation pipeline. (#14541) - **Visual analysis trigger tracking** β (#14399) - **Claude thinking signature sanitization** β History signatures sanitized when replaying Claude conversations. (#14499) - **Responses input media sanitization** β Assistant media sanitized in Responses input. (#14497) --- ## π 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 ~9Γ on large dirty trees. (#14338) --- ## π₯ Contributors Huge thanks to **18 contributors** who shipped **236 merged PRs** this cycle. @hezhijie0327 Β· @sxjeru Β· @yueyinqiu Β· @octo-patch Β· @hardy-one Β· @Coooolfan Β· @CanYuanA Β· @BillionClaw Β· @arvinxx Β· @tjx666 Β· @Innei Β· @neko Β· @AmAzing129 Β· @rdmclin2 Β· @lijian Β· @sudongyuer Β· @rivertwilight Β· @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.
π» Change Type
π Related Issue
π Description of Change
Introduces a "Try these tasks" recommendation section on the home page that suggests scheduled task templates tailored to the user's onboarding interests, then routes the one-click "create" action through
agentCronJobServiceso the resulting cron job is identical to manually-authored ones.Highlights:
content-creation,engineering,design,learning-research,business,marketing,product,personal-life) with per-template icon override (icon?: LucideIcon) and category-level fallback. Three templates declarerequiresSkillsfor OAuth (github,notionvia Klavis) and chained connections.TaskTemplateService.listDailyRecommend(interestKeys, { enabledSkillSources, excludeIds })β interest intersection match β seeded shuffle (stable peruserId Γ UTC date) β fallback topersonal-life/learning-researchβ fallback to remaining catalog. Skill-gated templates only enter the candidate pool when theirsourceis enabled server-side.user_task_template_interactions(migration0100) trackscreatedanddismissedinteractions per (user, templateId) so already-created or dismissed templates are excluded from future picks.useSkillConnectionconsolidates connect-state across LobeHub OAuth (popup +LOBEHUB_SKILL_AUTH_SUCCESSpostMessage) and Klavis MCP servers. Cards render a "Connect " CTA when any required skill is missing; once all dependencies resolve, the card flips to "Create". Skill stores are pre-fetched only when the recommendation actually contains an OAuth/Klavis-dependent template.parseCronPattern/formatScheduleTime/WEEKDAY_I18N_KEYSfrom the cron-config feature into@lobechat/utils/cronso both the cron editor and recommendation cards share the same parsing logic.taskTemplatenamespace (en-US,zh-CN) with title / description / prompt / schedule strings for all 19 templates plus action copy.π§ͺ How to Test
Coverage:
packages/const/src/taskTemplate.test.tsβ catalog shape invariantspackages/database/src/models/__tests__/userTaskTemplateInteraction.test.tsβ interaction persistencepackages/utils/src/cron.test.tsβ promoted cron parsing helperssrc/server/services/taskTemplate/index.test.tsβ recommendation pipeline (interest match, skill gating, fallbacks, exclusion, daily seed stability)src/hooks/useSkillConnection.test.tsβ connect-state aggregation across providersManual:
codinginterest β go to home β see GitHub-flavored templates.πΈ Screenshots / Videos
π Additional Information
users.interests(e.g. Chinese label vs canonical key) is currently handled best-effort on the client via the active onboarding locale; deeper normalization is tracked as a follow-up (LOBE-8261) and does not block this PR.TASK_TEMPLATE_FALLBACK_CATEGORIESis intentionally narrow (personal-life,learning-research) so users without matched interests still see useful generic picks instead of an empty section.