🐛 fix: fix group broadcast trigger tool use by arvinxx · Pull Request #11646 · lobehub/lobehub

arvinxx · 2026-01-20T10:19:00Z

💻 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

Propagate a new disableTools flag through agent runtime and group orchestration so broadcasted agent calls run without tools by default, and add tests to validate tool disabling behavior.

New Features:

Add a disableTools option to agent runtime execution and group orchestration parallel calls to control whether tools can be used.

Bug Fixes:

Ensure group broadcast agents run with tools disabled by default to avoid unintended tool usage during parallel calls.

Enhancements:

Guard tool manifest generation in the streaming executor when tools are disabled, and improve logging of broadcast calls with the disableTools flag.
Refine async task status handling switch formatting for better readability.

Tests:

Add unit tests for internal_createAgentState behavior when tools are disabled and for supervisor broadcast instructions including disableTools in parallel agent calls.

vercel · 2026-01-20T10:19:05Z

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

Project	Deployment	Review	Updated (UTC)
lobehub	Error		Jan 22, 2026 9:27am

sourcery-ai · 2026-01-20T10:19:07Z

Reviewer's Guide

Adds a disableTools flag to agent runtime and group orchestration broadcast flows so that broadcasted agents respond without invoking tools, wires this through the streaming executor, and strengthens tests around toolManifestMap behavior and group orchestration supervisor instructions. Also cleans up task status switch formatting and messaging.

Sequence diagram for broadcast group orchestration with disableTools

sequenceDiagram
  participant Supervisor as GroupOrchestrationSupervisor
  participant Store as GroupOrchestrationExecutors
  participant ChatSlice as StreamingExecutor
  participant ToolsEngine as AgentToolsEngine

  Note over Supervisor,Store: Supervisor decides to broadcast to multiple agents

  Supervisor->>Store: parallel_call_agents(instruction)
  Store->>Store: Extract agentIds, disableTools, toolMessageId
  Store->>Store: Prepare messageContext and messagesWithInstruction

  loop For each agentId
    Store->>ChatSlice: internal_execAgentRuntime({context.subAgentId=agentId, disableTools=true, messages, parentMessageId})
    ChatSlice->>ChatSlice: internal_execAgentRuntime extracts disableTools and context
    ChatSlice->>ChatSlice: streamingExecutor({disableTools, messages, parentMessageId, agentId, topicId, threadId})

    alt disableTools is false
      ChatSlice->>ToolsEngine: createAgentToolsEngine(model, provider)
      ChatSlice->>ToolsEngine: generateToolsDetailed(model, provider, pluginIds)
      ToolsEngine-->>ChatSlice: enabledToolIds
      ChatSlice->>ToolsEngine: getEnabledPluginManifests(enabledToolIds)
      ToolsEngine-->>ChatSlice: toolManifestMap
      ChatSlice->>ChatSlice: Execute agent runtime with tools
    else disableTools is true
      ChatSlice->>ChatSlice: Skip tools generation
      ChatSlice->>ChatSlice: Execute agent runtime without tools
    end
  end

Class diagram for updated group orchestration and streaming executor types

classDiagram
  class GroupOrchestrationSupervisor {
    -config
    +handleParallelCallAgents(params)
  }

  class SupervisorInstructionParallelCallAgentsPayload {
    +string[] agentIds
    +bool disableTools
    +string instruction
    +string toolMessageId
  }

  class SupervisorInstructionParallelCallAgents {
    +SupervisorInstructionParallelCallAgentsPayload payload
  }

  class GroupOrchestrationExecutors {
    +parallel_call_agents(instruction, state) GroupOrchestrationExecutorOutput
  }

  class StreamingExecutorAction {
    +string operationId
    +ConversationContext context
    +string agentId
    +bool disableTools
    +string topicId
    +string threadId
    +unknown initialState
    +string parentMessageId
    +string parentMessageType
    +Message[] messages
  }

  class InternalExecAgentRuntimeParams {
    +ConversationContext context
    +bool disableTools
    +Message[] messages
    +string parentMessageId
    +string parentMessageType
    +unknown initialState
  }

  class StreamingExecutor {
    +streamingExecutor(action StreamingExecutorAction) Promise~void~
    +internal_execAgentRuntime(params InternalExecAgentRuntimeParams) Promise~void~
  }

  class AgentToolsEngine {
    +generateToolsDetailed(model, provider, toolIds) ToolsDetailed
    +getEnabledPluginManifests(enabledToolIds) Map~string, PluginManifest~
  }

  class ConversationContext {
    +string agentId
    +string topicId
    +string threadId
    +string groupId
    +string subAgentId
    +string scope
  }

  GroupOrchestrationSupervisor --> SupervisorInstructionParallelCallAgents : constructs
  SupervisorInstructionParallelCallAgents *-- SupervisorInstructionParallelCallAgentsPayload : payload
  GroupOrchestrationSupervisor --> GroupOrchestrationExecutors : sends instructions
  GroupOrchestrationExecutors --> StreamingExecutor : internal_execAgentRuntime
  InternalExecAgentRuntimeParams --> ConversationContext : uses
  StreamingExecutorAction --> ConversationContext : context
  StreamingExecutor ..> AgentToolsEngine : uses when disableTools is false
  StreamingExecutorAction --> StreamingExecutor : input to streamingExecutor
  InternalExecAgentRuntimeParams --> StreamingExecutor : input to internal_execAgentRuntime

File-Level Changes

Change	Details	Files
Add disableTools support to agent runtime execution and tool manifest generation so tools can be globally disabled for a given execution	Extend StreamingExecutorAction and internal_execAgentRuntime params with an optional disableTools flag and plumb it through execution paths Guard tool manifest generation in streamingExecutor so toolsEngine is only constructed and enabledToolIds/toolManifestMap are populated when disableTools is not set or false Ensure internal_execAgentRuntime passes disableTools through to internal_createAgentState so toolManifestMap respects the flag	`src/store/chat/slices/aiChat/actions/streamingExecutor.ts`
Ensure group orchestration broadcasts run with tools disabled by default and propagate disableTools configuration through the orchestrator	Extend SupervisorInstructionParallelCallAgents payload with an optional disableTools flag and document its semantics Update GroupOrchestrationSupervisor to emit parallel_call_agents instructions with disableTools: true for broadcast decisions so broadcast agents do not call tools by default Update createGroupOrchestrationExecutors to log and forward disableTools into internal_execAgentRuntime for all broadcasted agent calls	`packages/agent-runtime/src/groupOrchestration/types.ts` `packages/agent-runtime/src/groupOrchestration/GroupOrchestrationSupervisor.ts` `src/store/chat/agents/GroupOrchestration/createGroupOrchestrationExecutors.ts`
Add tests to validate disableTools behavior for agent state creation and group orchestration supervisor instructions	Add tests for internal_createAgentState to assert toolManifestMap is empty when disableTools is true and populated/consistent when disableTools is false or undefined Update GroupOrchestrationSupervisor tests to assert that broadcast parallel_call_agents instructions include disableTools: true in the payload	`src/store/chat/slices/aiChat/actions/__tests__/streamingExecutor.test.ts` `packages/agent-runtime/src/groupOrchestration/__tests__/GroupOrchestrationSupervisor.test.ts`
Normalize task status switch-case formatting and behavior in group orchestration executors	Reformat the switch over task status to consistent indentation and explicit breaks Keep the behavior of updating tracker state and optimistic message content for completed, failed, and cancelled task states while improving readability	`src/store/chat/agents/GroupOrchestration/createGroupOrchestrationExecutors.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 · 2026-01-20T10:19:13Z

TestGru Assignment

Summary

Link	CommitId	Status	Reason
Detail	`c9519fe`	✅ Finished

History Assignment

Files

File	Pull Request
packages/agent-runtime/src/groupOrchestration/GroupOrchestrationSupervisor.ts	❌ Failed (I failed to setup the environment.)
src/store/chat/slices/aiChat/actions/streamingExecutor.ts	❌ Failed (I failed to setup the environment.)
src/store/chat/agents/GroupOrchestration/createGroupOrchestrationExecutors.ts	❌ Failed (I failed to setup the environment.)

Tip

You can @gru-agent and leave your feedback. TestGru will make adjustments based on your input

codecov · 2026-01-20T10:19:45Z

Codecov Report

❌ Patch coverage is 85.41667% with 14 lines in your changes missing coverage. Please review.
✅ Project coverage is 74.08%. Comparing base (f6988e7) to head (de70200).
⚠️ Report is 16 commits behind head on next.

Additional details and impacted files

@@            Coverage Diff             @@
##             next   #11646      +/-   ##
==========================================
- Coverage   82.82%   74.08%   -8.75%     
==========================================
  Files          85     1188    +1103     
  Lines        2358    94707   +92349     
  Branches      361    10867   +10506     
==========================================
+ Hits         1953    70162   +68209     
- Misses        397    24455   +24058     
- Partials        8       90      +82

Flag	Coverage Δ
app	`66.90% <85.26%> (?)`
database	`93.29% <ø> (?)`
packages/agent-runtime	`90.20% <100.00%> (?)`
packages/context-engine	`85.39% <ø> (?)`
packages/conversation-flow	`92.28% <ø> (?)`
packages/file-loaders	`88.66% <ø> (ø)`
packages/memory-user-memory	`69.68% <ø> (?)`
packages/model-bank	`100.00% <ø> (?)`
packages/model-runtime	`86.70% <ø> (?)`
packages/prompts	`79.33% <ø> (ø)`
packages/python-interpreter	`92.90% <ø> (?)`
packages/ssrf-safe-fetch	`0.00% <ø> (?)`
packages/utils	`93.25% <ø> (?)`
packages/web-crawler	`95.62% <ø> (?)`

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

Components	Coverage Δ
Store	`66.83% <79.41%> (∅)`
Services	`50.72% <100.00%> (∅)`
Server	`67.81% <0.00%> (∅)`
Libs	`41.13% <ø> (∅)`
Utils	`93.82% <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.

sourcery-ai

Hey - I've found 2 issues, and left some high level feedback:

In streamingExecutor.internal_createAgentState, the local enabledToolIds variable is assigned but never used, so consider either wiring it into the returned state (if needed) or removing it to avoid dead code.
In the new internal_createAgentState with disableTools tests, the vi.spyOn(agentConfigResolver, 'resolveAgentConfig') mock is not restored, which can leak state into other tests; consider calling mockRestore() or using vi.restoreAllMocks() in an afterEach.

Prompt for AI Agents

Please address the comments from this code review:

## Overall Comments
- In `streamingExecutor.internal_createAgentState`, the local `enabledToolIds` variable is assigned but never used, so consider either wiring it into the returned state (if needed) or removing it to avoid dead code.
- In the new `internal_createAgentState with disableTools` tests, the `vi.spyOn(agentConfigResolver, 'resolveAgentConfig')` mock is not restored, which can leak state into other tests; consider calling `mockRestore()` or using `vi.restoreAllMocks()` in an `afterEach`.

## Individual Comments

### Comment 1
<location> `src/store/chat/slices/aiChat/actions/__tests__/streamingExecutor.test.ts:1419-1428` </location>
<code_context>
+  describe('internal_createAgentState with disableTools', () => {
</code_context>

<issue_to_address>
**suggestion (testing):** Strengthen the `disableTools: true` test by ensuring tools are actually configured but still not used.

This test only checks that `toolManifestMap` is `{}` when `disableTools` is `true`, but it never configures any plugins/tools. As a result, it would also pass if there were simply no tools available. To better validate the behavior, mock `resolveAgentConfig` (as in the second test) to return at least one plugin and assert that `toolManifestMap` remains empty. That will confirm tools are skipped specifically due to `disableTools`.

Suggested implementation:

```typescript
  describe('internal_createAgentState with disableTools', () => {
    it('should return empty toolManifestMap when disableTools is true', async () => {
      act(() => {
        useChatStore.setState({ internal_execAgentRuntime: realExecAgentRuntime });
      });

      // Ensure tools/plugins are configured but should be ignored due to disableTools
      const resolveAgentConfigMock = resolveAgentConfig as jest.MockedFunction<typeof resolveAgentConfig>;
      resolveAgentConfigMock.mockResolvedValue({
        plugins: [
          {
            id: 'test-plugin',
            name: 'Test Plugin',
            tools: [
              {
                name: 'test-tool',
                displayName: 'Test Tool',
                description: 'A test tool to ensure tools are configured',
                parameters: {
                  type: 'object',
                  properties: {},
                },
              },
            ],
          },
        ],
      } as any);

      const { result } = renderHook(() => useChatStore());
      const userMessage = {
        id: TEST_IDS.USER_MESSAGE_ID,
        role: 'user',
        content: TEST_CONTENT.USER_MESSAGE,

```

1. The snippet above assumes:
   - `resolveAgentConfig` is imported into this test file.
   - Jest is being used, and `resolveAgentConfig` can be treated as `jest.MockedFunction`.
2. You already mentioned there is a second test in this file that mocks `resolveAgentConfig`. To stay consistent with the existing test suite:
   - Use the same import source and mocking style as that second test (e.g., `jest.spyOn(module, 'resolveAgentConfig')` or `vi.spyOn` if using Vitest).
   - If the other test uses `jest.spyOn`, replace the `const resolveAgentConfigMock = ...` line with the same pattern, for example:
     ```ts
     const resolveAgentConfigMock = jest.spyOn(agentConfigModule, 'resolveAgentConfig');
     resolveAgentConfigMock.mockResolvedValue(/* same object as above */);
     ```
3. After the code that calls `internal_createAgentState`, add/ensure an assertion exists that checks `toolManifestMap` is empty, e.g.:
   ```ts
   expect(agentState.toolManifestMap).toEqual({});
   ```
   If you already had such an assertion, no additional change is needed beyond the mock itself.
4. If your test framework is Vitest instead of Jest, replace `jest.MockedFunction` and `jest.spyOn` with the corresponding `vi` APIs to match the rest of the file.
</issue_to_address>

### Comment 2
<location> `src/store/chat/slices/aiChat/actions/__tests__/streamingExecutor.test.ts:1447-1456` </location>
<code_context>
+    it('should include tools in toolManifestMap when disableTools is false or undefined', async () => {
</code_context>

<issue_to_address>
**suggestion (testing):** Also assert that the toolManifestMap is non-empty when tools are enabled to better prove the behavior.

Right now the test would still pass if both maps were empty (e.g., if no tools were actually enabled). Please add an assertion that `toolManifestMap` is non-empty (for example, `expect(Object.keys(stateWithoutDisable.toolManifestMap).length).toBeGreaterThan(0);`) so the test verifies that tools are truly configured when `disableTools` is not true.

Suggested implementation:

```typescript
      const stateWithoutDisable = useChatStore.getState();
      expect(Object.keys(stateWithoutDisable.toolManifestMap).length).toBeGreaterThan(0);

```

If the variable holding the state in this test is not named `stateWithoutDisable`, replace `stateWithoutDisable` in the new expectation with the actual state variable name used in the `"should include tools in toolManifestMap when disableTools is false or undefined"` test. The new assertion should be placed after the state is read and before the test's final expectations/return.
</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/store/chat/slices/aiChat/actions/streamingExecutor.ts

lobehubbot · 2026-01-22T09:37:20Z

❤️ Great PR @arvinxx ❤️

The growth of the project is inseparable from user feedback and contributions. 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 lobe-chat development and sharing AI news from 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.339](v2.0.0-next.338...v2.0.0-next.339) <sup>Released on **2026-01-22**</sup> #### ♻ Code Refactoring - **misc**: Move vercel-react-best-practices skills to .agents directory. #### ✨ Features - **misc**: Skill setting page and skill store. #### 🐛 Bug Fixes - **model-runtime**: Filter unsupported image types (SVG) before sending to vision models. - **misc**: Fix group broadcast trigger tool use, fix local system tools. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### Code refactoring * **misc**: Move vercel-react-best-practices skills to .agents directory, closes [#11703](#11703) ([6df7731](6df7731)) #### What's improved * **misc**: Skill setting page and skill store, closes [#11665](#11665) ([d8c0c26](d8c0c26)) #### What's fixed * **model-runtime**: Filter unsupported image types (SVG) before sending to vision models, closes [#11698](#11698) ([c0c99a7](c0c99a7)) * **misc**: Fix group broadcast trigger tool use, closes [#11646](#11646) ([831a9b3](831a9b3)) * **misc**: Fix local system tools, closes [#11702](#11702) ([6548fc7](6548fc7)) </details> <div align="right"> [![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top) </div>

lobehubbot · 2026-01-22T11:43:08Z

🎉 This PR is included in version 2.0.0-next.339 🎉

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>

dosubot bot added the size:L This PR changes 100-499 lines, ignoring generated files. label Jan 20, 2026

dosubot bot added the 🐛 Bug label Jan 20, 2026

arvinxx changed the title ~~🐛 fix: fix group broadcast issue~~ 🐛 fix: fix group broadcast will trigger tool use Jan 20, 2026

arvinxx changed the title ~~🐛 fix: fix group broadcast will trigger tool use~~ 🐛 fix: fix group broadcast trigger tool use Jan 20, 2026

sourcery-ai bot reviewed Jan 20, 2026

View reviewed changes

vercel bot deployed to Preview January 20, 2026 11:06 View deployment

arvinxx force-pushed the fix/group-broadcast branch from c9519fe to abed2c7 Compare January 20, 2026 13:01

vercel bot deployed to Preview January 20, 2026 15:40 View deployment

fix broadcast issue

e476c6a

arvinxx force-pushed the fix/group-broadcast branch from abed2c7 to e476c6a Compare January 22, 2026 03:32

github-code-quality bot found potential problems Jan 22, 2026

View reviewed changes

src/store/chat/slices/aiChat/actions/streamingExecutor.ts Fixed Show fixed Hide fixed

arvinxx added 2 commits January 22, 2026 11:40

fix broadcast

ec7eacc

fix broadcast

51f237a

vercel bot deployed to Preview January 22, 2026 04:50 View deployment

fix group slug

de70200

vercel bot had a problem deploying to Preview January 22, 2026 09:27 Failure

arvinxx merged commit 831a9b3 into next Jan 22, 2026
34 of 36 checks passed

arvinxx deleted the fix/group-broadcast branch January 22, 2026 09:37

lobehubbot added the released on @next label Jan 22, 2026

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

🐛 fix: fix group broadcast trigger tool use#11646

🐛 fix: fix group broadcast trigger tool use#11646
arvinxx merged 4 commits intonextfrom
fix/group-broadcast

arvinxx commented Jan 20, 2026 •

edited by sourcery-ai bot

Loading

Uh oh!

vercel bot commented Jan 20, 2026 •

edited

Loading

Uh oh!

sourcery-ai bot commented Jan 20, 2026 •

edited

Loading

Interacting with Sourcery

Customizing Your Experience

Getting Help

Uh oh!

gru-agent bot commented Jan 20, 2026 •

edited

Loading

Uh oh!

codecov bot commented Jan 20, 2026 •

edited

Loading

Uh oh!

sourcery-ai bot left a comment

Uh oh!

Uh oh!

Uh oh!

lobehubbot commented Jan 22, 2026 •

edited

Loading

Uh oh!

lobehubbot commented Jan 22, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Uh oh!

Conversation

arvinxx commented Jan 20, 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 20, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

sourcery-ai bot commented Jan 20, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Reviewer's Guide

Sequence diagram for broadcast group orchestration with disableTools

Class diagram for updated group orchestration and streaming executor types

File-Level Changes

Interacting with Sourcery

Customizing Your Experience

Getting Help

Uh oh!

gru-agent bot commented Jan 20, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

TestGru Assignment

Summary

Files

Uh oh!

codecov bot commented Jan 20, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Codecov Report

Uh oh!

sourcery-ai bot left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

lobehubbot commented Jan 22, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

lobehubbot commented Jan 22, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

arvinxx commented Jan 20, 2026 •

edited by sourcery-ai bot

Loading

vercel bot commented Jan 20, 2026 •

edited

Loading

sourcery-ai bot commented Jan 20, 2026 •

edited

Loading

gru-agent bot commented Jan 20, 2026 •

edited

Loading

codecov bot commented Jan 20, 2026 •

edited

Loading

lobehubbot commented Jan 22, 2026 •

edited

Loading