🐛 fix: fix multi agent tasks issue by arvinxx · Pull Request #11672 · lobehub/lobehub

arvinxx · 2026-01-21T03:21:56Z

💻 Change Type

🔗 Related Issue

🔀 Description of Change

🧪 How to Test

Tested locally
Added/updated tests
No tests needed

📸 Screenshots / Videos

Before	After
...	...

📝 Additional Information

Summary by Sourcery

Enable parallel multi-agent task execution in the orchestration pipeline while improving task UI metrics and rendering for both client and server modes.

New Features:

Add group orchestration support and executor wiring for triggering multiple async tasks in parallel and rendering multi-task requests in the UI.

Bug Fixes:

Refresh chat messages after task batch results to keep multi-task tool and message state in sync.

Enhancements:

Split task rendering into dedicated client and server task item components and add task metrics display (steps, tool calls, elapsed or total time).
Preload tool render components to avoid Suspense loading flashes when expanding tool results.
Adjust system role guidance and manifest to temporarily disable the multi-task tool entry while keeping the underlying infrastructure in place.

Tests:

Update group management executor tests to cover the new triggerExecuteTasks orchestration callback.

vercel · 2026-01-21T03:22:02Z

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Review	Updated (UTC)
lobehub	Canceled		Jan 21, 2026 5:03am

sourcery-ai · 2026-01-21T03:22:04Z

Reviewer's Guide

Implements proper support for multi-agent parallel tasks by wiring a new executeAgentTasks orchestration path end-to-end, splitting client/server task rendering with live metrics, enhancing task title metrics display, and updating batch-result handling and system prompts while temporarily disabling the public manifest entry for the multi-task tool.

Sequence diagram for executeAgentTasks orchestration flow

sequenceDiagram
  actor User
  participant UI as ChatUI
  participant Supervisor as SupervisorAgent
  participant Tool as GroupManagementExecutor
  participant AR as AgentRuntime
  participant Orchestr as GroupOrchestrationStore
  participant Agents as WorkerAgents
  participant StreamExec as StreamingExecutor
  participant ChatStore

  User->>UI: Ask for multi-part work
  UI->>Supervisor: User request
  Supervisor->>Tool: executeAgentTasks(params)
  Tool->>Tool: prepare tasks list
  Tool->>Tool: ctx.registerAfterCompletion(callback)
  Tool-->>Supervisor: BuiltinToolResult { stop: true,
  Tool-->>Supervisor:   state.type = executeAgentTasks }

  Supervisor->>AR: Continue group orchestration
  AR->>Tool: Complete tool call
  Tool-->>AR: afterCompletion callback registered

  AR->>Tool: Finish execution
  Tool-->>Orchestr: triggerExecuteTasks(params)

  Orchestr->>Orchestr: get().activeGroupId
  Orchestr->>Orchestr: build initialResult
  Orchestr->>Orchestr: decision = execute_tasks
  Orchestr->>AR: internal_execGroupOrchestration({
  Orchestr->>AR:   initialResult.type = supervisor_decided,
  Orchestr->>AR:   payload.decision = execute_tasks,
  Orchestr->>AR:   payload.params.tasks, toolMessageId,
  Orchestr->>AR:   skipCallSupervisor
  Orchestr->>AR: })

  AR->>Agents: Run tasks in parallel
  loop For each task
    AR-->>Agents: Execute async task
    Agents-->>AR: Task result
  end

  AR-->>StreamExec: result.nextContext.phase = tasks_batch_result

  StreamExec->>ChatStore: refreshMessages(context)
  ChatStore-->>UI: Updated messages with task results
  UI-->>User: Display completed multi-agent tasks

Class diagram for TaskItem refactor and metrics components

classDiagram
  class UIChatMessage {
    +string id
    +any content
    +any metadata
    +any taskDetail
  }

  class TaskItem {
    +UIChatMessage item
  }

  class ClientTaskItem {
    +UIChatMessage item
  }

  class ServerTaskItem {
    +UIChatMessage item
  }

  class TaskTitle {
    +TaskMetrics metrics
    +ThreadStatus status
    +string title
  }

  class MetricsDisplay {
    +TaskMetrics metrics
    +ThreadStatus status
    -number elapsedTime
    -setElapsedTime(number value) void
  }

  class TaskMetrics {
    +number duration
    +boolean isLoading
    +number startTime
    +number steps
    +number toolCalls
  }

  class ClientTaskStats {
    +boolean isLoading
    +number startTime
    +number steps
    +number toolCalls
  }

  class useClientTaskStats {
    +ClientTaskStats useClientTaskStats(boolean enabled, string threadId)
  }

  class ThreadStatus {
    <<enumeration>>
    Completed
    Failed
    Cancel
  }

  TaskItem --> UIChatMessage : uses
  TaskItem --> ClientTaskItem : renders
  TaskItem --> ServerTaskItem : renders

  ClientTaskItem --> UIChatMessage : reads
  ClientTaskItem --> TaskTitle : renders
  ClientTaskItem --> useClientTaskStats : calls

  ServerTaskItem --> UIChatMessage : reads
  ServerTaskItem --> TaskTitle : renders

  TaskTitle --> TaskMetrics : has
  TaskTitle --> MetricsDisplay : renders

  MetricsDisplay --> TaskMetrics : reads
  MetricsDisplay --> ThreadStatus : reads

  useClientTaskStats --> ClientTaskStats : returns
  useClientTaskStats --> UIChatMessage : derives from thread messages

File-Level Changes

Change	Details	Files
Add metrics display and client/server variants for task items to support client-mode multi-agent tasks with live progress stats.	Extend TaskTitle with TaskMetrics interface and MetricsDisplay component showing steps, tool calls, and elapsed/total time using shared formatters and i18n. Introduce ClientTaskItem and ServerTaskItem components, selected by taskDetail.clientMode, to render tasks differently for client and server modes while reusing shared state components. Implement useClientTaskStats hook to fetch thread messages for client-mode tasks and compute steps, tool call counts, and start time for live metrics. Optimize TaskItem memoization by switching to fast-deep-equal for item prop comparison.	`src/features/Conversation/Messages/Tasks/TaskItem/TaskTitle.tsx` `src/features/Conversation/Messages/Tasks/TaskItem/index.tsx` `src/features/Conversation/Messages/Tasks/TaskItem/ClientTaskItem.tsx` `src/features/Conversation/Messages/Tasks/TaskItem/ServerTaskItem.tsx` `src/features/Conversation/Messages/Tasks/TaskItem/useClientTaskStats.ts`
Wire a new executeAgentTasks flow for parallel task execution through group orchestration, executor, types, and UI render, while hiding it from the public tool manifest and system prompt patterns.	Comment out executeAgentTasks declaration in the GroupManagement manifest and remove executeAgentTasks references from the systemRole workflow patterns and guidance, simplifying to executeAgentTask-only patterns. Define TriggerExecuteTaskItem and TriggerExecuteTasksParams plus triggerExecuteTasks callback in shared types and expose them through the builtin tool slice types. Add triggerExecuteTasks action in the groupOrchestration slice to start orchestration with a supervisor_decided decision='execute_tasks' and pass tasks and toolMessageId, and include it in getGroupOrchestrationCallbacks. Implement executeAgentTasks in GroupManagementExecutor to register an afterCompletion hook calling ctx.groupOrchestration.triggerExecuteTasks and return a stop=true result with state metadata. Register a client-side ExecuteTasksRender component, which displays each task with agent avatar, title, timeout, and read-only instruction, and hook it into GroupManagementRenders. Update executor tests to account for the new triggerExecuteTasks callback in mocked orchestration contexts.	`packages/builtin-tool-group-management/src/manifest.ts` `packages/builtin-tool-group-management/src/systemRole.ts` `packages/types/src/tool/builtin.ts` `src/store/chat/slices/aiAgent/actions/groupOrchestration.ts` `packages/builtin-tool-group-management/src/executor.ts` `packages/builtin-tool-group-management/src/executor.test.ts` `packages/builtin-tool-group-management/src/client/Render/index.ts` `packages/builtin-tool-group-management/src/client/Render/ExecuteTasks/index.tsx` `src/store/tool/slices/builtin/types.ts`
Improve batch tool/task completion handling and tool render UX for multi-agent executions.	Update streamingExecutor to treat both tasks_batch_result and tools_batch_result phases as batch completions that require a refreshMessages call to avoid race conditions. Add preloadToolRenderComponents helper to eagerly import tool Detail and Debug render components when tool calls are detected, avoiding Suspense flashes on first expand.	`src/store/chat/slices/aiChat/actions/streamingExecutor.ts` `src/features/Conversation/Messages/Tool/preload.ts`

Tips and commands

Interacting with Sourcery

Trigger a new review: Comment @sourcery-ai review on the pull request.
Continue discussions: Reply directly to Sourcery's review comments.
Generate a GitHub issue from a review comment: Ask Sourcery to create an
issue from a review comment by replying to it. You can also reply to a
review comment with @sourcery-ai issue to create an issue from it.
Generate a pull request title: Write @sourcery-ai anywhere in the pull
request title to generate a title at any time. You can also comment
@sourcery-ai title on the pull request to (re-)generate the title at any time.
Generate a pull request summary: Write @sourcery-ai summary anywhere in
the pull request body to generate a PR summary at any time exactly where you
want it. You can also comment @sourcery-ai summary on the pull request to
(re-)generate the summary at any time.
Generate reviewer's guide: Comment @sourcery-ai guide on the pull
request to (re-)generate the reviewer's guide at any time.
Resolve all Sourcery comments: Comment @sourcery-ai resolve on the
pull request to resolve all Sourcery comments. Useful if you've already
addressed all the comments and don't want to see them anymore.
Dismiss all Sourcery reviews: Comment @sourcery-ai dismiss on the pull
request to dismiss all existing Sourcery reviews. Especially useful if you
want to start fresh with a new review - don't forget to comment
@sourcery-ai review to trigger a new review!

Customizing Your Experience

Access your dashboard to:

Enable or disable review features such as the Sourcery-generated pull request
summary, the reviewer's guide, and others.
Change the review language.
Add, remove or edit custom review instructions.
Adjust other review settings.

Getting Help

Contact our support team for questions or feedback.
Visit our documentation for detailed guides and information.
Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.

gru-agent · 2026-01-21T03:22:09Z

There is too much information in the pull request to test.

sourcery-ai

Hey - I've found 1 issue, and left some high level feedback:

The TaskItem memoization now uses fast-deep-equal on the full UIChatMessage, which could be expensive for large message trees; consider memoizing based on stable keys (e.g., id plus specific fields you care about) or splitting props to avoid deep equality on the whole object.
ClientTaskItem and ServerTaskItem share a lot of identical UI and status-handling logic; extracting a common presentational component that accepts metrics as props would reduce duplication and make future changes to task rendering less error-prone.

Prompt for AI Agents

Please address the comments from this code review:

## Overall Comments
- The `TaskItem` memoization now uses `fast-deep-equal` on the full `UIChatMessage`, which could be expensive for large message trees; consider memoizing based on stable keys (e.g., `id` plus specific fields you care about) or splitting props to avoid deep equality on the whole object.
- `ClientTaskItem` and `ServerTaskItem` share a lot of identical UI and status-handling logic; extracting a common presentational component that accepts metrics as props would reduce duplication and make future changes to task rendering less error-prone.

## Individual Comments

### Comment 1
<location> `packages/builtin-tool-group-management/src/client/Render/ExecuteTasks/index.tsx:73-77` </location>
<code_context>
+
+  return (
+    <div className={styles.container}>
+      {tasksWithAgents.map((task, index) => {
+        const timeoutMinutes = task.timeout ? Math.round(task.timeout / 60_000) : 30;
+
+        return (
+          <div className={styles.taskCard} key={task.agentId || index}>
+            <Flexbox gap={12}>
+              {/* Header: Agent info + Timeout */}
</code_context>

<issue_to_address>
**issue (bug_risk):** Avoid potential key collisions when multiple tasks use the same agentId.

Since multiple tasks can legitimately share an `agentId`, using it alone as the React key (with `index` only as a falsy fallback) risks incorrect reconciliation and subtle UI glitches. Prefer a composite key like `${agentId}-${index}` or, better, a stable task-specific identifier to ensure each rendered task is uniquely keyed.
</issue_to_address>

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}

src/features/Conversation/Messages/Tasks/TaskItem/TaskTitle.tsx

🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

chatgpt-codex-connector

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 1b19255999

ℹ️ 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 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

chatgpt-codex-connector · 2026-01-21T03:26:50Z

src/store/chat/slices/aiAgent/actions/groupOrchestration.ts

+      initialResult: {
+        type: 'supervisor_decided',
+        payload: {
+          decision: 'execute_tasks',
+          params: { tasks, toolMessageId },


Wire execute_tasks to batch_exec_async_tasks

When triggerExecuteTasks sets decision: 'execute_tasks', the GroupOrchestrationSupervisor decision switch only handles execute_task and falls through to the default case (finish with unknown_decision). This means any call to the new executeAgentTasks flow will immediately end orchestration without running the parallel tasks. To make this work, the supervisor needs an execute_tasks branch that emits batch_exec_async_tasks (and maps the task payload) instead of finishing.

Useful? React with 👍 / 👎.

codecov · 2026-01-21T03:32:03Z

Codecov Report

❌ Patch coverage is 16.66667% with 30 lines in your changes missing coverage. Please review.
✅ Project coverage is 74.05%. Comparing base (af234ac) to head (80fc170).
⚠️ Report is 8 commits behind head on next.

Additional details and impacted files

@@            Coverage Diff             @@
##             next   #11672      +/-   ##
==========================================
- Coverage   74.07%   74.05%   -0.03%     
==========================================
  Files        1187     1187              
  Lines       94490    94524      +34     
  Branches    12860    10394    -2466     
==========================================
+ Hits        69996    70001       +5     
- Misses      24404    24433      +29     
  Partials       90       90

Flag	Coverage Δ
app	`66.89% <16.66%> (-0.03%)`	⬇️
database	`93.29% <ø> (ø)`
packages/agent-runtime	`90.20% <ø> (ø)`
packages/context-engine	`85.29% <ø> (ø)`
packages/conversation-flow	`92.37% <ø> (ø)`
packages/file-loaders	`88.66% <ø> (ø)`
packages/memory-user-memory	`69.75% <ø> (ø)`
packages/model-bank	`100.00% <ø> (ø)`
packages/model-runtime	`86.70% <ø> (ø)`
packages/prompts	`79.33% <ø> (ø)`
packages/python-interpreter	`92.90% <ø> (ø)`
packages/ssrf-safe-fetch	`0.00% <ø> (ø)`
packages/utils	`93.25% <ø> (ø)`
packages/web-crawler	`95.62% <ø> (ø)`

Flags with carried forward coverage won't be shown. Click here to find out more.

Components	Coverage Δ
Store	`66.83% <16.66%> (-0.09%)`	⬇️
Services	`50.81% <ø> (ø)`
Server	`67.82% <ø> (ø)`
Libs	`41.13% <ø> (ø)`
Utils	`93.82% <ø> (ø)`

🚀 New features to boost your workflow:

❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

lobehubbot · 2026-01-21T08:12:03Z

❤️ Great PR @arvinxx ❤️

The growth of project is inseparable from user feedback and contribution. Thanks for your contribution! If you are interested in the lobehub developer community, please join our discord and then dm @arvinxx or @canisminor1990. They will invite you to our private developer channel. We are talking about the lobe-chat development or sharing AI newsletter around the world.

This comment was translated by Claude.

Original Content

❤️ Great PR @arvinxx ❤️

The growth of project is inseparable from user feedback and contribution, thanks for your contribution! If you are interesting with the lobehub developer community, please join our discord and then dm @arvinxx or @canisminor1990. They will invite you to our private developer channel. We are talking about the lobe-chat development or sharing ai newsletter around the world.

## [Version 2.0.0-next.330](v2.0.0-next.329...v2.0.0-next.330) <sup>Released on **2026-01-21**</sup> #### 🐛 Bug Fixes - **misc**: Fix multi agent tasks issue. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### What's fixed * **misc**: Fix multi agent tasks issue, closes [#11672](#11672) ([9de773b](9de773b)) </details> <div align="right"> [![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top) </div>

lobehubbot · 2026-01-21T08:30:19Z

🎉 This PR is included in version 2.0.0-next.330 🎉

The release is available on:

Your semantic-release bot 📦🚀

## [Version 1.153.0](v1.152.0...v1.153.0) <sup>Released on **2026-01-23**</sup> #### ♻ Code Refactoring - **auth**: Remove NEXT_PUBLIC_AUTH_URL env variable. - **model-select**: Migrate FunctionCallingModelSelect to LobeSelect. - **ModelSwitchPanel**: Migrate from Popover to DropdownMenu with virtual scrolling. - **userMemories**: Removed un-used code. - **misc**: Improve memory data with experience and identity, move vercel-react-best-practices skills to .agents directory. #### ✨ Features - **database**: Added user memory activity. - **desktop**: Add legacy local database detection and migration guidance. - **misc**: Add platform-aware download client menu option, add server version check for desktop app, remove Clerk authentication code, skill setting page and skill store, support agent group unpublish agents, support client tasks mode, update the sandbox preinstall libs in sys role. #### 🐛 Bug Fixes - **copilot**: Pass correct scope when creating new session in PageEditor. - **desktop**: Gracefully handle missing update manifest 404 errors. - **model-runtime**: Filter unsupported image types (SVG) before sending to vision models. - **pdf**: Upgrade pdfjs-dist and react-pdf to v5.x. - **sidebar-drawer**: Fix drawer positioning and title style. - **misc**: Fix group broadcast trigger tool use, fix local system tools, fix memory schema, fix multi agent tasks issue, fix multi tasks no summary issue, fix scope issue, fix tool argument scape and improve multi task run, fixed the sandbox tools call when error should use right callback, improve e2e server and complete i18n resources, slove the agent group editor not focus in editdata area, slove the agents header switch agents the lobeAI not show problem, sloved the old removeSessionTopics not work, TypewriterEffect not refreshing on language change, updata cron job ui & fixed commnuity pagenation goto error, update the agentbuilder tools not always use humanIntervention. #### 💄 Styles - **misc**: Improve auto scroll and group profile, update og, update share style. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### Code refactoring * **auth**: Remove NEXT_PUBLIC_AUTH_URL env variable, closes [lobehub#11658](https://github.com/jaworldwideorg/OneJA-Bot/issues/11658) ([c0f9875](c0f9875)) * **model-select**: Migrate FunctionCallingModelSelect to LobeSelect, closes [lobehub#11664](https://github.com/jaworldwideorg/OneJA-Bot/issues/11664) ([ad51305](ad51305)) * **ModelSwitchPanel**: Migrate from Popover to DropdownMenu with virtual scrolling, closes [lobehub#11663](https://github.com/jaworldwideorg/OneJA-Bot/issues/11663) ([c9d9dff](c9d9dff)) * **userMemories**: Removed un-used code, closes [lobehub#11713](https://github.com/jaworldwideorg/OneJA-Bot/issues/11713) ([89750fc](89750fc)) * **misc**: Improve memory data with experience and identity, closes [lobehub#11717](https://github.com/jaworldwideorg/OneJA-Bot/issues/11717) ([bdb3eb4](bdb3eb4)) * **misc**: Move vercel-react-best-practices skills to .agents directory, closes [lobehub#11703](https://github.com/jaworldwideorg/OneJA-Bot/issues/11703) ([6df7731](6df7731)) #### What's improved * **database**: Added user memory activity, closes [lobehub#11680](https://github.com/jaworldwideorg/OneJA-Bot/issues/11680) ([0160fbd](0160fbd)) * **desktop**: Add legacy local database detection and migration guidance, closes [lobehub#11682](https://github.com/jaworldwideorg/OneJA-Bot/issues/11682) ([5664b84](5664b84)) * **misc**: Add platform-aware download client menu option, closes [lobehub#11676](https://github.com/jaworldwideorg/OneJA-Bot/issues/11676) ([55abddc](55abddc)) * **misc**: Add server version check for desktop app, closes [lobehub#11710](https://github.com/jaworldwideorg/OneJA-Bot/issues/11710) ([0cf2723](0cf2723)) * **misc**: Remove Clerk authentication code, closes [lobehub#11711](https://github.com/jaworldwideorg/OneJA-Bot/issues/11711) ([395595a](395595a)) * **misc**: Skill setting page and skill store, closes [lobehub#11665](https://github.com/jaworldwideorg/OneJA-Bot/issues/11665) ([d8c0c26](d8c0c26)) * **misc**: Support agent group unpublish agents, closes [lobehub#11687](https://github.com/jaworldwideorg/OneJA-Bot/issues/11687) ([4e060be](4e060be)) * **misc**: Support client tasks mode, closes [lobehub#11666](https://github.com/jaworldwideorg/OneJA-Bot/issues/11666) ([98cf57b](98cf57b)) * **misc**: Update the sandbox preinstall libs in sys role, closes [lobehub#11688](https://github.com/jaworldwideorg/OneJA-Bot/issues/11688) ([404c577](404c577)) #### What's fixed * **copilot**: Pass correct scope when creating new session in PageEditor, closes [lobehub#11714](https://github.com/jaworldwideorg/OneJA-Bot/issues/11714) ([0259270](0259270)) * **desktop**: Gracefully handle missing update manifest 404 errors, closes [lobehub#11625](https://github.com/jaworldwideorg/OneJA-Bot/issues/11625) ([13e95b9](13e95b9)) * **model-runtime**: Filter unsupported image types (SVG) before sending to vision models, closes [lobehub#11698](https://github.com/jaworldwideorg/OneJA-Bot/issues/11698) ([c0c99a7](c0c99a7)) * **pdf**: Upgrade pdfjs-dist and react-pdf to v5.x, closes [lobehub#11686](https://github.com/jaworldwideorg/OneJA-Bot/issues/11686) ([2b620df](2b620df)) * **sidebar-drawer**: Fix drawer positioning and title style, closes [lobehub#11655](https://github.com/jaworldwideorg/OneJA-Bot/issues/11655) ([cf5320e](cf5320e)) * **misc**: Fix group broadcast trigger tool use, closes [lobehub#11646](https://github.com/jaworldwideorg/OneJA-Bot/issues/11646) ([831a9b3](831a9b3)) * **misc**: Fix local system tools, closes [lobehub#11702](https://github.com/jaworldwideorg/OneJA-Bot/issues/11702) ([6548fc7](6548fc7)) * **misc**: Fix memory schema, closes [lobehub#11645](https://github.com/jaworldwideorg/OneJA-Bot/issues/11645) ([3baf780](3baf780)) * **misc**: Fix multi agent tasks issue, closes [lobehub#11672](https://github.com/jaworldwideorg/OneJA-Bot/issues/11672) ([9de773b](9de773b)) * **misc**: Fix multi tasks no summary issue, closes [lobehub#11685](https://github.com/jaworldwideorg/OneJA-Bot/issues/11685) ([26ce317](26ce317)) * **misc**: Fix scope issue, closes [lobehub#11719](https://github.com/jaworldwideorg/OneJA-Bot/issues/11719) ([17adde8](17adde8)) * **misc**: Fix tool argument scape and improve multi task run, closes [lobehub#11691](https://github.com/jaworldwideorg/OneJA-Bot/issues/11691) ([b13bb8a](b13bb8a)) * **misc**: Fixed the sandbox tools call when error should use right callback, closes [lobehub#11721](https://github.com/jaworldwideorg/OneJA-Bot/issues/11721) ([e8fce68](e8fce68)) * **misc**: Improve e2e server and complete i18n resources, closes [lobehub#11678](https://github.com/jaworldwideorg/OneJA-Bot/issues/11678) ([d450dd9](d450dd9)) * **misc**: Slove the agent group editor not focus in editdata area, closes [lobehub#11677](https://github.com/jaworldwideorg/OneJA-Bot/issues/11677) ([9ac84e6](9ac84e6)) * **misc**: Slove the agents header switch agents the lobeAI not show problem, closes [lobehub#11726](https://github.com/jaworldwideorg/OneJA-Bot/issues/11726) ([f45f508](f45f508)) * **misc**: Sloved the old removeSessionTopics not work, closes [lobehub#11671](https://github.com/jaworldwideorg/OneJA-Bot/issues/11671) ([06d41e5](06d41e5)) * **misc**: TypewriterEffect not refreshing on language change, closes [lobehub#11657](https://github.com/jaworldwideorg/OneJA-Bot/issues/11657) ([ba30f46](ba30f46)) * **misc**: Updata cron job ui & fixed commnuity pagenation goto error, closes [lobehub#11700](https://github.com/jaworldwideorg/OneJA-Bot/issues/11700) ([42ad2a0](42ad2a0)) * **misc**: Update the agentbuilder tools not always use humanIntervention, closes [lobehub#11696](https://github.com/jaworldwideorg/OneJA-Bot/issues/11696) ([0d3017b](0d3017b)) #### Styles * **misc**: Improve auto scroll and group profile, closes [lobehub#11725](https://github.com/jaworldwideorg/OneJA-Bot/issues/11725) ([550acc2](550acc2)) * **misc**: Update og, closes [lobehub#11709](https://github.com/jaworldwideorg/OneJA-Bot/issues/11709) ([01cf4e4](01cf4e4)) * **misc**: Update share style, closes [lobehub#11716](https://github.com/jaworldwideorg/OneJA-Bot/issues/11716) ([3c70dfa](3c70dfa)) </details> <div align="right"> [![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top) </div>

arvinxx added 2 commits January 21, 2026 11:13

improve run multi tasks ui

5053ae2

improve group mode

1b19255

dosubot bot added the size:XL This PR changes 500-999 lines, ignoring generated files. label Jan 21, 2026

dosubot bot added the 🐛 Bug label Jan 21, 2026

sourcery-ai bot reviewed Jan 21, 2026

View reviewed changes

github-code-quality bot found potential problems Jan 21, 2026

View reviewed changes

src/features/Conversation/Messages/Tasks/TaskItem/TaskTitle.tsx Fixed Show fixed Hide fixed

🐛 fix: remove unused isCompleted variable in TaskTitle

80fc170

🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

chatgpt-codex-connector bot reviewed Jan 21, 2026

View reviewed changes

vercel bot deployed to Preview January 21, 2026 05:03 View deployment

arvinxx merged commit 9de773b into next Jan 21, 2026
38 of 40 checks passed

arvinxx deleted the feat/support-multi-agent-tasks branch January 21, 2026 08:11

lobehubbot added the released on @next label Jan 21, 2026

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

🐛 fix: fix multi agent tasks issue#11672

🐛 fix: fix multi agent tasks issue#11672
arvinxx merged 3 commits intonextfrom
feat/support-multi-agent-tasks

arvinxx commented Jan 21, 2026 •

edited by sourcery-ai bot

Loading

Uh oh!

vercel bot commented Jan 21, 2026 •

edited

Loading

Uh oh!

sourcery-ai bot commented Jan 21, 2026 •

edited

Loading

Interacting with Sourcery

Customizing Your Experience

Getting Help

Uh oh!

gru-agent bot commented Jan 21, 2026 •

edited

Loading

Uh oh!

sourcery-ai bot left a comment

Uh oh!

Uh oh!

chatgpt-codex-connector bot left a comment

Uh oh!

chatgpt-codex-connector bot Jan 21, 2026

Uh oh!

codecov bot commented Jan 21, 2026 •

edited

Loading

Uh oh!

Uh oh!

lobehubbot commented Jan 21, 2026 •

edited

Loading

Uh oh!

lobehubbot commented Jan 21, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Uh oh!

Conversation

arvinxx commented Jan 21, 2026 • edited by sourcery-ai bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

💻 Change Type

🔗 Related Issue

🔀 Description of Change

🧪 How to Test

📸 Screenshots / Videos

📝 Additional Information

Summary by Sourcery

Uh oh!

vercel bot commented Jan 21, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

sourcery-ai bot commented Jan 21, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Reviewer's Guide

Sequence diagram for executeAgentTasks orchestration flow

Class diagram for TaskItem refactor and metrics components

File-Level Changes

Interacting with Sourcery

Customizing Your Experience

Getting Help

Uh oh!

gru-agent bot commented Jan 21, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

sourcery-ai bot left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

chatgpt-codex-connector bot left a comment

Choose a reason for hiding this comment

💡 Codex Review

Uh oh!

chatgpt-codex-connector bot Jan 21, 2026

Choose a reason for hiding this comment

Uh oh!

codecov bot commented Jan 21, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Codecov Report

Uh oh!

Uh oh!

lobehubbot commented Jan 21, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

lobehubbot commented Jan 21, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

arvinxx commented Jan 21, 2026 •

edited by sourcery-ai bot

Loading

vercel bot commented Jan 21, 2026 •

edited

Loading

sourcery-ai bot commented Jan 21, 2026 •

edited

Loading

gru-agent bot commented Jan 21, 2026 •

edited

Loading

codecov bot commented Jan 21, 2026 •

edited

Loading

lobehubbot commented Jan 21, 2026 •

edited

Loading