v.26.8.29.1

Estimated reading: 6 minutes

This release delivers new features, new components, enhancements, and bug fixes across Robility Flow and its component ecosystem to improve system usability and overall platform performance.

Limitation

1. Invoke Flow: Component nodes may break when multiple chat outputs are configured within the flow.

New Feature

Flow introduces new tools to deliver deeper visibility into workflow execution and overall automation performance:

1. Flow Analytics Dashboard: Track workflow execution and performance in real time. Users can view key execution metrics, analyze operational trends, pinpoint component-level bottlenecks, and jump directly to Traces for fast troubleshooting.

2. Flow Insights: Stay in control of your workflows with a real-time visualization tool that provides a comprehensive view of flow execution. Monitor component interactions, track execution progress, and quickly assess status through visual highlights within a single, searchable, and filterable interface for faster diagnostics and improved workflow health.

Limitations
a. Flow Insights Zoom: Zooming is unavailable for the starting component of any flow; navigation and zoom focus begin from the second component onward.
b. Parallel Execution Zoom Behavior: When a workflow runs with parallel execution, Run Focus zooms to whichever component completes first rather than following sequential order.
   Workaround: Toggle off the Run Focus option while running parallel flow executions.

New Component

Flow introduces new components to improve secure application access, workflow routing, and execution control across automation flows.

1. Robility OCR Extractor: Extract text and structured information from images and PDF files seamlessly. This component uses OpenAI-compatible vision endpoints to process visual data accurately.

2. App Integration Token: Manage and provide authentication tokens automatically across external services. It eliminates manual credential handling by fetching tokens securely when required during execution. This ensures seamless, enterprise-grade security for all connected applications.

3. Workflow Pass-Through: Forward incoming data from the primary input directly to the next step without modification. It provides precise execution control to streamline conditional routing across complex flows. This component is ideal for simplifying data management, flow testing, and debugging.

4. Token Optimizer: Compress input content dynamically while preserving core context and meaning. It triggers based on custom token thresholds and target retention percentages, delivering optimized text alongside real-time compression metrics.

Enhancements

1. Configuration Support: Added deployment name input fields for Azure OpenAI and Embedding Models in Robility Manager. Robility Flow now automatically fetches these configured deployment names, enabling Robility LLM, KB Ingestion, and KB Retrieval components to dynamically utilize them during execution.

2. File Format Support: Enabled .tiff and .tif image formats across Save File, Read, and Search Users can now input and process .tiff and .tif file paths directly within Robility Flow to expand document processing capabilities.

3. Control Plane Prompt Loader: Upgraded the prompt loader component to support fetching prompts using production, latest, or version-specific flags, giving users greater precision and control over prompt retrieval.

4. Empty Flow Publishing: Enhanced Robility Flow to restrict the publishing of empty or incomplete workflows.

Flow Bug Fix

1. Flow Scheduler Status Management
Fixed an issue where flows could remain stuck in Run Initiated status indefinitely.

a. Execution Timeout: Flows that don’t begin execution within 3 minutes are now automatically marked as Failed, with the status synced to Robility Manager.
b. Downtime Recovery: Flows interrupted by application or server downtime are now detected on restart, marked as Failed, and synced to Robility Manager.

2.Model Provider

a. Toggle: Fixed an issue where the toggle within the Model Provider component was disabled. The toggle now works properly, allowing users to enable and manage provider configurations.

b. Project-Level Access: Model Provider integrations are no longer restricted to individual accounts. Access is now tied to the project, allowing all authorized team members in the same workspace to use the configured providers.

Component Bug Fix

1. Multi-Project Dropdown Retrieval
Fixed an issue where having multiple projects within a single tenant caused dropdowns to fail to display values in DataTable, Interact (Get & Add), Credentials, and Invoke Flow. Dropdown values are now retrieved consistently and accurately regardless of how many projects exist under the tenant.

2. REST API Component
Fixed an issue where invalid data formats caused request errors. The Request Body field now includes an automatic formatting tool that cleans up and checks your data structure before sending, reducing configuration errors.

3. Invoke Flow
Fixed an issue where Tool Mode was not working. Also added a refresh option to the version field’s list for easier access to updated versions.

Existing Limitations

1. A user cannot edit or schedule a flow that has already been scheduled by another user within the same project.

2. The Model Provider integration is currently accessible only to the user who configured it. Other users within the same project or agent cannot access or use the configured integration.
Workaround: Use the LLM component by passing the required LLM connection as an input. This enables other users to utilize the LLM functionality without requiring direct access to the configured Model Provider integration.

3.The Pulse Component does not support variable mapping for the Security Key and Public Key input fields when dynamically loading prompts.
Workaround: The component works as expected when the values are provided directly instead of using variable mapping.

4. Version History will track only workflows published after the upgrade. Previously published versions remained available in Robility Manager but will not appear in Version History or be eligible for scheduling. To enable these features, export and rename the workflow (for example, FlowName.1.0.0 → FlowName), then republish it.

5. The Loop component has been enhanced to resolve stale and duplicate Datatable updates. Updating the component will remove all nodes within the Loop component and associated Datatable values. Back up the workflow before upgrading.

6. When processing large files with the Read File component, increase the Timeout and Retry Count settings to ensure successful OCR extraction.

7. The invoke flow in tool mode does not work with the configured slug name.
Workaround: After connecting the tool node, manually update the slug name before using it.

Known Issues

1. The embedding functionality in the Robility LLM component is currently not working.(Tentative fix: Sept 2026) 
2. Deleting a project also removes all associated flows, and they cannot be recovered.(Tentative fix: Sept 2026) 
3. If the description field is removed from the flow JSON before import, the workflow is still uploaded with an empty description. (Tentative fix: Sept 2026)
4. Flow names are user-specific, allowing multiple users to create flows with the same name, which may result in duplicate solution names and versions. (Tentative fix: Sept 2026)
5. Newly generated API keys currently apply to all workflow versions; this will be updated to restrict keys to specific versions in a future release.(Tentative fix: Sept 2026)
6. The Web Scraper component does not support extracting data from JavaScript-based web pages. (Tentative fix: Sept 2026)

Release Date: 29.08.2026

Share this Doc

v.26.8.29.1

Or copy link

CONTENTS
Robility Chatbot
Robility Assistant
Online