Skip to main content

Release 1.2.7

Version: 1.2.7

Release Date: 2.9.2026

Release Type: Minor Release

Summary​

This release adds Graphs as a connected knowledge surface, gives agents a clearer harness for planned and delegated work, introduces role-based permission management and ZIP ingestion for Manual Upload, and adds Mobile App and Desktop App eligibility controls for agents. It also introduces an isolated Sandbox for command and file workflows, makes Siesta AI easier to connect to compatible MCP clients through OAuth, and improves navigation in long conversations.

New Features​

Graphs​

  • Teams can create and govern Graphs, inspect their catalog and lifecycle information, and explore connected knowledge through search, filters, neighborhoods, and the 3D Galaxy View.
  • Graphs can be assigned to Agents as read-only knowledge, with controlled write access available for supported internal scenarios.
  • Developers can work with Graphs through the documented REST API and MCP tools for graph discovery, nodes, edges, neighborhoods, and bounded subgraphs.

Agent Harness​

  • Planning mode lets an Agent present its intended approach before starting supported multi-step work.
  • Conversation-scoped Todo lists make the active item and completed work visible without creating duplicate organizational tasks.
  • Background agents allow supported, delegable parts of a request to continue through the configured Agent harness.

Sandbox and Published Artifacts​

  • Agents can run commands in an isolated Linux Sandbox whose conversation workspace persists between calls.
  • Selected attachments can be staged into the workspace, and completed files are exposed to the user only after the Agent explicitly publishes them.
  • Published outputs remain associated with the assistant message so users can open or download the intended artifact without exposing internal working files.

Roles and Permissions​

  • Users > Roles provides built-in and custom roles with a searchable, grouped permission catalog and member management.
  • Users can hold multiple roles; their effective access combines the permissions granted by those roles.
  • Role management prevents privilege escalation: managers can grant or assign only permissions they hold, while Owner membership and the requirement to keep at least one active Owner are protected.

ZIP Upload for Data Sources​

  • Manual Upload accepts top-level ZIP archives and imports their supported entries as individual Data files while preserving safe relative paths.
  • Nested archives, unsafe or unreadable entries, and entries that exceed extraction limits are skipped. The Web App warns when a source was created with skipped archive entries.

Mobile and Desktop App Agent Visibility​

  • Agent creation and Agents > Interfaces include Mobile App and Desktop App eligibility controls when those interfaces are enabled for the organization.
  • App eligibility remains separate from Access: the signed-in user must also be allowed to use the agent. The setting controls interface-filtered selection and does not by itself reveal Chat in a client build where Chat is hidden or activation-dependent.

New Integrations​

Siesta AI MCP OAuth​

  • Profile > Apps & Extensions now provides an OAuth setup path for connecting compatible external AI clients to Siesta AI as an MCP server.
  • The consent flow identifies the requesting client, shows the requested access, and returns the user to the originating client after approval or cancellation.
  • API key and npx setup remain available as separate alternatives for compatible client environments.

Improvements​

Long Conversation Navigation​

  • Conversations with at least five user turns provide a transcript outline that tracks the current position and jumps to user messages in long internal and full shared-conversation views.
  • The compact trigger keeps the outline readable while streaming updates add new user turns.
Last updated on