Skip to content

gallery

v1.0.14 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

Published 15d Model Serving & MLOps
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Affected surfaces

auth

Summary

AI summary

Experimental Model Context Protocol support and new agent skills such as calendar integration and scheduled notifications are introduced.

Changes in this release

Feature Medium

Introduced experimental support for Model Context Protocol (MCP).

Introduced experimental support for Model Context Protocol (MCP).

Source: granite4.1:8b-q6_K@2026-05-19

Confidence: high

 —
Feature Medium

Added user permission flow for MCP tool calls with approval prompt.

Added user permission flow for MCP tool calls with approval prompt.

Source: granite4.1:8b-q6_K@2026-05-19

Confidence: high

 —
Feature Medium

Enabled execution support for models on Pixel TPUs, including sideloaded models.

Enabled execution support for models on Pixel TPUs, including sideloaded models.

Source: granite4.1:8b-q6_K@2026-05-19

Confidence: high

 —
Feature Medium

Added `create-calendar-event` and `read-calendar-events` skills directly from chat.

Added `create-calendar-event` and `read-calendar-events` skills directly from chat.

Source: granite4.1:8b-q6_K@2026-05-19

Confidence: high

 —
Feature Medium

Introduced `schedule-notification` skill with Notification Management Screen and deep-link support.

Introduced `schedule-notification` skill with Notification Management Screen and deep-link support.

Source: granite4.1:8b-q6_K@2026-05-19

Confidence: high

 —
Feature Medium

Updated UI for Chat and Prompt Lab to match official Gemini app experience.

Updated UI for Chat and Prompt Lab to match official Gemini app experience.

Source: granite4.1:8b-q6_K@2026-05-19

Confidence: high

 —
Feature Medium

Added UI integration and core storage for dynamic System Prompt customization.

Added UI integration and core storage for dynamic System Prompt customization.

Source: granite4.1:8b-q6_K@2026-05-19

Confidence: high

 —
Feature Medium

Introduced chat history saving supporting text, images, and audio messages.

Introduced chat history saving supporting text, images, and audio messages.

Source: granite4.1:8b-q6_K@2026-05-19

Confidence: high

 —
Feature Medium

Comprehensive documentation added for MCP.

Comprehensive documentation added for MCP.

Source: granite4.1:8b-q6_K@2026-05-19

Confidence: low

 —
Feature Medium

Added configuration options and engine initialization for speculative decoding to improve generation speed.

Added configuration options and engine initialization for speculative decoding to improve generation speed.

Source: granite4.1:8b-q6_K@2026-05-19

Confidence: low

 —
Feature Medium

Added `learn-something-new` skill to the agent.

Added `learn-something-new` skill to the agent.

Source: granite4.1:8b-q6_K@2026-05-19

Confidence: low

 —
Feature Medium

Enabled direct download and sharing of images from the chat.

Enabled direct download and sharing of images from the chat.

Source: granite4.1:8b-q6_K@2026-05-19

Confidence: low

 —
Bugfix Medium

Fixed session reset issues when turning off skills or deleting chat history.

Fixed session reset issues when turning off skills or deleting chat history.

Source: granite4.1:8b-q6_K@2026-05-19

Confidence: high

 —
Bugfix Medium

Switched from exact to inexact alarms for improved Android permission compliance.

Switched from exact to inexact alarms for improved Android permission compliance.

Source: granite4.1:8b-q6_K@2026-05-19

Confidence: high

 —
Bugfix Medium

Disabled several older skills (calculate-hash, text-spinner, send-email) by default.

Disabled several older skills (calculate-hash, text-spinner, send-email) by default.

Source: granite4.1:8b-q6_K@2026-05-19

Confidence: low

 —
Bugfix Medium

Resolved `NumberFormatException` crash in Benchmark Results Viewer for non-US locales.

Resolved `NumberFormatException` crash in Benchmark Results Viewer for non-US locales.

Source: granite4.1:8b-q6_K@2026-05-19

Confidence: low

 —
Full changelog

What's Changed

1. Experimental Model Context Protocol (MCP) Support

  • Introduced experimental support for MCP.
  • Added a user permission flow for MCP tool calls, ensuring users are prompted for approval before the agent executes a tool (with an option to "Always allow").
  • Added comprehensive documentation for MCP.

2. Hardware & Performance Enhancements

  • Pixel TPU Support: Enabled execution support for models on Pixel TPUs, including support for sideloaded models.
  • Speculative Decoding: Added configuration options and engine initialization for speculative decoding to improve model generation speed.

3. New Agent Skills & Capabilities

  • Calendar Integration: Added new skills to create-calendar-event and read-calendar-events directly from the chat.
  • Scheduled Notifications: Added a schedule-notification skill (for one-time or daily alerts), complete with a Notification Management Screen and deep-link support that opens the agent chat with a pre-filled query when tapped.
  • Learn Something New: Introduced a new learn-something-new skill.
  • Note: Several older skills (like calculate-hash, text-spinner, send-email) were disabled by default to refine the default agent experience.

4. UI & Chat Experience Improvements

  • Gemini-like UI: Updated the UI for both Chat and Prompt Lab to better match the official Gemini app experience.
  • System Prompt Customization: Added UI integration and core storage for users to edit and retrieve dynamic System Prompts.
  • Chat History: Introduced chat history saving that supports text, images, and audio messages.
  • Media Handling: Added a new feature allowing users to download and share images directly from the chat.

5. Notable Bug Fixes & Stability

  • Fixed session reset issues when turning off skills or deleting chat history.
  • Switched from using "exact alarms" to "inexact alarms" to improve Android permission compliance.
  • Fixed a NumberFormatException crash in the Benchmark Results Viewer that occurred for non-US locales (e.g., parsing "8186,03").

New Contributors

  • @kuishou68 made their first contribution in https://github.com/google-ai-edge/gallery/pull/629
  • @yijie-yang made their first contribution in https://github.com/google-ai-edge/gallery/pull/837

Full Changelog: https://github.com/google-ai-edge/gallery/compare/1.0.13...1.0.14

View diff on GitHub

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Share on X Share on Bluesky

Track gallery

Get notified when new releases ship.

Sign up free

About gallery

A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally.

All releases →

Related context

Beta — feedback welcome: [email protected]