📌 Release Overview

• 2026.08

• Unique hosted: February 18, 2026

• Self hosted: February 25, 2026

Chat Platform

🚀 What’s New (Business/End-User Focus)

User External Prompt Links Require Confirmation: Prompts opened via external links will be pre-filled but won’t auto-submit; users must explicitly confirm before sending, reducing unintended execution and aligning with modern security best practices.

Admin EXPERIMENTAL Voice Input with Whisper Speech-to-Text: A new Whisper-based voice input mode is now available in the chat input. It features real-time audio waveform visualization during recording and a processing indicator while transcription is in progress. See Whisper Transcription Service for setup and deployment options.

🎨 UI / UX Refresh of Chat Interface

This release advances our UI/UX modernization initiative with a refreshed chat interface focused on clarity, consistency, and ease of use. The new chat UI is currently in Experimental state, opt-in and disabled by default. It can be enabled upon request via feature flag for selected users or environments.

User EXPERIMENTAL Chat Welcome View: Warmer, more inviting entry: “How can I help you?” with a short description. The large, always-on upload area is removed; upload is available via drag-and-drop into the chat box or via a less prominent control, so the main focus is on asking a question. This new UI is not enabled by default (but can be enabled via the corresponding feature flag mentioned in the Infrastructure Changes) as it part of the UI refresh we are working on.

User EXPERIMENTAL Buttons inside the chat box: Chat input actions (upload, voice, tools, send) are moved inside the chat input area for a cleaner, more consistent look. Upload and voice are de‑emphasized so they’re not confused with the primary send action, while still easy to find when needed.

User EXPERIMENTAL Simpler prompt menu: My Prompts and Suggested Prompts are in a compact bar below the input with clear labels, so you can open and pick prompts faster.

User EXPERIMENTAL Easier tool selection: Tool selection is available via a “+” menu, with grouped tools (MCP tools) in dropdown groups for easier separation of concerns.

🔧 Improvements

Admin EXPERIMENTAL Secure HTML Rendering via HTML Store: HTML content generated in chat responses (e.g. financial charts, rendered HTML blocks) is now served through a dedicated HTML Store service with TTL-based memory management. Large HTML content (>2MB) shows a download button instead of rendering inline. See Code Reflector Infrastructure for details.

🐞 Bug Fixes

User Backslash Display in User Messages: Double backslashes now display correctly instead of being collapsed into fewer backslashes.

RAG

🚀 What’s New (Business/End-User Focus)

User EXPERIMENTAL Email File Ingestion (.eml and .msg): You can now upload and ingest Outlook .msg and standard .eml email files. Email body text is extracted and cleaned (signatures and quoted replies are stripped), and attachments are automatically converted and included.

Admin EXPERIMENTAL Skip CSV File Ingestion: You can now choose to skip the ingestion of CSV files by setting the new SKIP_EXCEL_INGESTION flag as the uniqueIngestionMode. This gives you greater flexibility to customize your ingestion process and focus only on the file types that matter most to your workflow.

Admin EXPERIMENTAL Reporting Engine (.uqtemplate): A new reporting engine allows automated report generation from ingested content using customizable .uqtemplate template files. Configure reportTemplates in the ingestion settings to trigger report generation on ingestion. Generated .uqreport outputs are stored as new content items.

Admin BETA File Access:

File-based access control is now available for all clients in the Knowledge Base, enabling permissions to be configured at the individual file level rather than only at the folder level.

This provides greater flexibility when managing sensitive or team-specific content, ensuring that access can be tailored precisely to business needs without restructuring folders.

User EXPERIMENTAL Multi-File Select and Move In Knowledge Base Column View:
Multi-file selection capabilities are now available in Column View, making it faster and more intuitive to organize content within the Knowledge Base.

Files can be selected using familiar desktop interaction patterns:

• Shift + Click to select a range

• Cmd (Mac) / Ctrl (Windows) + Click to select non-adjacent files

This update reduces repetitive actions and enables faster restructuring of content within large Knowledge Bases.

Agentic Table

🔧 Improvements

User UI Polish for Agentic Table: Consolidated UI refinements including a refreshed rerun button, improved dropdowns on the sheet overview, a new loading preview for the agentic table, and updated inline reference badges for consistent styling and clearer readability.

User Collapsible Content Support in Agentic Table Cells: Cells now support HTML details/summary for accessible, styled expand/collapse with proper overflow handling.

User RfPAgent Subagent: Persistent Chat Context: Subagents now reuse a persistent chat_id via ShortTermMemory, enabling them to understand and leverage broader conversation and table context – not just single lines – so follow-up questions are answered more reliably.

🐞 Bug Fixes

User Consistent Reference Colors in Multi-Answer Columns: Reference badges in Agentic Table now strictly follow our design tokens and behave correctly in Multi Answer columns, ensuring accurate colors, proper per-column mapping, and visual parity across default and hover states.

Unique AI

🔧 Improvements

🐞 Bug Fixes

User Correct Indentation for Bullet Formatting: Resolved an issue where user instructions for nested bullet points were not applied correctly when formatting text. Bullet levels such as • (single indent) and o (double indent) are now rendered with the expected spacing, improving copy-paste into documents. This change applies only to newly created spaces and does not affect existing ones.

Language Model

🚀 What’s New (Business/End-User Focus)

Admin Model-Agnostic Token Counting: Token counting has been refactored to be model-agnostic, removing the tight dependency on the OpenAI tokenizer and enabling accurate accounting across supported LLMs. The tokenizer can now be configured directly within the Language Model settings. Currently supported tokenizers include OpenAI encoders as well as Qwen and DeepSeek, with additional tokenizers available on request. When switching models, ensure the tokenizer is correctly adjusted in the Language Model Info configuration to maintain accurate token tracking.

New Model Deployments:

Anthropic

Admin Claude Opus 4.6 is available through LiteLLM using the following enum:

• litellm:anthropic-claude-opus-4-6

xAI

Admin Grok 4.1 models are available through LiteLLM using the following enum:

• litellm:grok-4-1-fast-non-reasoning

• litellm:grok-4-1-fast-reasoning