3.16.3 Release Notes

3.16.3 Release Notes#

Squirro 3.16.3 was released on July 8, 2026.

Learn more about the Squirro Release Process page.

Improvements#

AI#

  • Added native support for Anthropic models in Squirro Chat, including a dedicated Anthropic chat model configuration (model, API key, and optional base URL) and cleaner, Anthropic-specific settings that omit parameters that don’t apply, such as temperature and reasoning effort. Chat conversations can now call the Anthropic API directly instead of only being reachable indirectly through AWS Bedrock, and projects using Anthropic no longer fail due to unrelated model settings.

  • Added support for image input in chat. Authorized models can now receive images as part of a conversation, and vision-capable agents can inspect uploaded images to answer questions about their content.

  • Added Speech to Chat support in the embedded chat widget. Administrators can enable microphone / speech-to-text input for end users under App & Navbar settings, “Enable Speech to Text” → “Embedded Chat Widget”.

  • Added a Model Context Protocol (MCP) aggregator server that exposes tools from installed Studio plugins to MCP-compatible clients over a spec-compliant Streamable-HTTP transport, with project-scoped access and permission checks.

Platform#

  • Cluster Users and Workspace Admins on workspaces-enabled instances can now see edit and delete actions for widgets, themes, and dashboard loaders.

Bug Fixes#

  • Fixed an error that could prevent a chat model from being created when using the Google provider with certain timeout configurations.

Installation and Upgrade#

For new installations, find step-by-step instructions on the Install and Manage Squirro with Ansible page (recommended) and Installing Squirro on Linux pages.

To upgrade an existing installation, see the Upgrading Squirro page.


Contents