> ## Documentation Index
> Fetch the complete documentation index at: https://docs.artaios.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Known Issues & Limitations

> Current platform limitations, known bugs, and workarounds

<Info>
  This page is actively maintained. Issues are resolved in priority order based on impact and user feedback.
</Info>

***

## Current Limitations

### Platform Constraints

<AccordionGroup>
  <Accordion title="Global Knowledge Bases & Tools" icon="database" defaultOpen>
    **Status**: Removed in v0.2.1

    Global knowledge bases and tools have been removed to simplify configuration. All knowledge bases and tools must now be configured per agent.

    **Migration**: Move global configurations to individual agent definitions.

    ```yaml theme={null}
    # ❌ Old approach (no longer supported)
    global:
      knowledge_bases: [kb1, kb2]
      tools: [tool1, tool2]

    # ✅ New approach
    agents:
      - name: my_agent
        knowledge_bases: [kb1, kb2]
        tools: [tool1, tool2]
    ```
  </Accordion>

  <Accordion title="Manual RAG Deprecation" icon="triangle-exclamation">
    **Status**: Deprecated, removal planned for v0.3

    Manual RAG (Retrieval-Augmented Generation) configuration is being phased out in favor of UKnow integration.

    **Action Required**: Migrate to UKnow for knowledge base management before v0.3 release.

    **Timeline**: Manual RAG will be fully removed in v0.3 (December 2025)
  </Accordion>

  <Accordion title="Model Provider Availability" icon="server">
    Not all model providers support all features:

    * **Tool Calling**: Not supported by Magistral, devstral-medium, mistral-moderation, and mistral-saba models
    * **Vision**: Limited to specific models (see [Model Selection](/documentation/agent_config/types_config/model-selection))
    * **Streaming**: Supported by most models, but may have provider-specific limitations
  </Accordion>
</AccordionGroup>

***

## Known Issues

### High Priority

<AccordionGroup>
  <Accordion title="Boolean Edge Key Interpretation" icon="code-branch" defaultOpen>
    **Issue**: Boolean edge keys `yes` and `no` are interpreted as `True`/`False` in YAML parsing.

    **Impact**: Conditional edges with boolean routing may fail or route incorrectly.

    **Workaround**: Use quoted keys in your YAML configuration:

    ```yaml theme={null}
    edges:
      - from: decision_agent
        condition: "Should we proceed?"
        condition_type: boolean
        routing:
          "yes": approval_agent  # ✅ Quoted
          "no": rejection_agent  # ✅ Quoted
    ```

    **Status**: Fix planned for v0.2.2
  </Accordion>

  <Accordion title="First Message Timing in AMAS Chat" icon="message">
    **Issue**: The first user message in AMAS Chat appears after the first agent message instead of before.

    **Impact**: Chat history display order is incorrect for the initial exchange.

    **Workaround**: None currently. This is a UI display issue and doesn't affect functionality.

    **Status**: Fix in progress
  </Accordion>
</AccordionGroup>

### Medium Priority

<AccordionGroup>
  <Accordion title="OneDrive SharePoint Cross-Query" icon="microsoft">
    **Issue**: OneDrive configuration also queries from SharePoint sites when using broad drive IDs.

    **Impact**: May retrieve documents from unintended SharePoint locations.

    **Workaround**: Only include drive IDs ending with `.../me/<your_email>` to limit scope to personal OneDrive:

    ```yaml theme={null}
    knowledge_base:
      provider: uknow
      config:
        sources:
          - type: onedrive
            drive_id: "https://graph.microsoft.com/v1.0/me/your.email@company.com"
    ```

    **Status**: Investigating improved filtering options
  </Accordion>

  <Accordion title="Window Context Loss" icon="window">
    **Issue**: Switching browser windows or tabs may cause loss of selected agent context.

    **Impact**: Users need to reselect their agent after switching windows.

    **Status**: Fixed in v0.2.1

    <Check>
      This issue has been resolved. Update to v0.2.1 or later.
    </Check>
  </Accordion>

  <Accordion title="Authorization UI Update" icon="shield-check">
    **Issue**: Authorized UI doesn't update immediately after successful authorization.

    **Impact**: Users may not see authorization status change without page refresh.

    **Status**: Fixed in v0.2.1

    <Check>
      This issue has been resolved. Update to v0.2.1 or later.
    </Check>
  </Accordion>
</AccordionGroup>

### Low Priority

<AccordionGroup>
  <Accordion title="Google Drive Security Status" icon="google">
    **Issue**: Google Drive provider is marked as "insecure" in UKnow integration.

    **Impact**: Google Drive integration is available but flagged with security warning.

    **Reason**: UKnow is currently undergoing security re-issuance for Google Drive OAuth.

    **Status**: Official support coming shortly after security certification
  </Accordion>

  <Accordion title="Pydantic Error Messages" icon="triangle-exclamation">
    **Issue**: Pydantic validation error messages could be more user-friendly.

    **Impact**: Technical error messages may be difficult for non-developers to understand.

    **Status**: Improved in v0.2.1

    <Check>
      Error messages have been enhanced in v0.2.1 with clearer, more actionable feedback.
    </Check>
  </Accordion>
</AccordionGroup>

***

## Feature Limitations

### Agent Configuration

<Tabs>
  <Tab title="Workflow Constraints">
    **Current Limitations:**

    * Maximum of 50 agents per workflow
    * Maximum of 100 edges per workflow
    * Circular dependencies are not automatically detected (will cause runtime errors)
    * Parallel execution limited to 10 concurrent agents

    **Planned Improvements (v0.3):**

    * Automatic circular dependency detection
    * Increased parallel execution limits
    * Workflow validation before deployment
  </Tab>

  <Tab title="Knowledge Base">
    **Current Limitations:**

    * Maximum file size: 50MB per file
    * Supported formats: PDF, DOCX, TXT, MD, CSV, XLSX
    * Maximum collection size: 1000 files
    * Indexing time: Up to 5 minutes for large documents

    **Planned Improvements (v0.3):**

    * Support for additional file formats (PPT, HTML)
    * Faster indexing with incremental updates
    * Larger file size support (up to 100MB)
  </Tab>

  <Tab title="Tool Calling">
    **Current Limitations:**

    * Maximum of 20 tools per agent
    * Tool execution timeout: 30 seconds
    * No support for streaming tool outputs
    * Limited error recovery for failed tool calls

    **Planned Improvements (v0.3):**

    * Configurable tool timeouts
    * Automatic retry logic for transient failures
    * Streaming tool outputs for long-running operations
  </Tab>

  <Tab title="API & Integration">
    **Current Limitations:**

    * WebSocket connection timeout: 5 minutes of inactivity
    * REST API rate limit: 100 requests/minute per user
    * Maximum message size: 1MB
    * Session history limited to last 100 messages

    **Planned Improvements (v0.3):**

    * Configurable WebSocket timeouts
    * Higher rate limits for enterprise users
    * Extended session history options
  </Tab>
</Tabs>

***

## Performance Considerations

### Response Times

<CardGroup cols={2}>
  <Card title="Typical Response Times" icon="clock" iconType="duotone">
    * **Simple LLM Agent**: 1-3 seconds
    * **React Agent with Tools**: 3-10 seconds
    * **Multi-Agent Workflow**: 5-30 seconds
    * **Vision/OCR Tasks**: 5-15 seconds
  </Card>

  <Card title="Factors Affecting Speed" icon="gauge" iconType="duotone">
    * Model selection (GPT-4o is faster)
    * Number of tools available
    * Knowledge base size
    * Workflow complexity
    * Image/document size
  </Card>
</CardGroup>

<Tip>
  For latency-sensitive applications, use GPT-4o or Mistral Medium models and limit the number of tools per agent.
</Tip>

### Token Usage

<Warning>
  **Context Window Management**: Large knowledge bases and long conversation histories can quickly consume token limits.
</Warning>

**Best Practices:**

* Use `include_history: true` with `history_length: 5` instead of `include_full_history: true`
* Implement conversation summarization for long sessions
* Limit knowledge base scope to relevant documents
* Use structured outputs to reduce response verbosity

***

## Reporting Issues

<Steps>
  <Step title="Check This Page" icon="magnifying-glass">
    Verify if your issue is already documented with a workaround
  </Step>

  <Step title="Search Documentation" icon="book">
    Review relevant documentation sections for configuration guidance
  </Step>

  <Step title="Gather Information" icon="clipboard">
    Collect error messages, YAML configuration, and steps to reproduce
  </Step>

  <Step title="Contact Support" icon="envelope">
    Email **[lorenz.stirnweis@arttacsolutions.de](mailto:lorenz.stirnweis@arttacsolutions.de)** with:

    * Clear description of the issue
    * Expected vs actual behavior
    * Configuration snippets (remove sensitive data)
    * Screenshots if applicable
  </Step>
</Steps>

***

## Issue Tracking

<CardGroup cols={3}>
  <Card title="Report Bug" icon="bug" iconType="duotone" color="#dc2626" href="mailto:lorenz.stirnweis@arttacsolutions.de?subject=Bug Report">
    **Subject**: "Bug: \[Brief Description]"
  </Card>

  <Card title="Request Feature" icon="lightbulb" iconType="duotone" color="#f59e0b" href="mailto:lorenz.stirnweis@arttacsolutions.de?subject=Feature Request">
    **Subject**: "Feature Request: \[Your Idea]"
  </Card>

  <Card title="Get Help" icon="life-ring" iconType="duotone" color="#0ea5e9" href="mailto:lorenz.stirnweis@arttacsolutions.de?subject=Support Request">
    **Subject**: "Support: \[Your Question]"
  </Card>
</CardGroup>

***

## Update Frequency

<Note>
  This page is updated with each release. Last updated: **November 2025** (v0.2.1)
</Note>

<Card title="View Release Notes" icon="newspaper" iconType="duotone" color="#6366F1" href="/documentation/platform/release-notes">
  See what's been fixed and what's new in the latest releases
</Card>