> ## Documentation Index
> Fetch the complete documentation index at: https://docs.activeviam.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Changelog

For details about versioning, see our [Versioning Policy](https://docs.activeviam.com/atoti-eos.html).

<Update label="6.1.23" description="2026-07-10">
  ### Added

  * PIVOT-14139 Visualize This: The chat assistant now uses the Tool Search Tool pattern for dynamic tool discovery.
    Instead of sending every available tool to the model at the start of a conversation, the model is offered a single
    synthetic search tool and retrieves only the relevant tools on demand. This reduces token consumption and improves
    tool-selection accuracy.

  * PIVOT-14122 Visualize This: Added a Python API for the chat assistant. `Session.chat` exposes the chat configuration
    from the Atoti Python SDK, including `Chat.system_prompt` to read and customize the system prompt directly from
    Python. See [Set up Visualize This in Python](../developer-guide/enable-ai-tools/visualize-this/setup-python).

  * PYTHON-922 Auto-Explain: Added a Python API to configure Auto-Explain from the Atoti Python SDK. `Cube.auto_explain`
    exposes the tuning constants, including drill-down depth, absolute and relative contribution thresholds, the
    variation threshold, entropy and member limits, and included or excluded hierarchies overall and per measure. See
    [Set up Auto-Explain in Python](../developer-guide/enable-ai-tools/auto-explain/setup-python).

  ### Changed

  * PYTHON-859 Auto-Explain: Root-cause analysis (root-cause members, contribution percentages, and contribution tables)
    no longer requires an LLM and is always available without an AI provider configured. An LLM is now only required for
    the optional AI summary. When no LLM is configured, the AI summary is unavailable.
    See [How to set up Auto-Explain](../developer-guide/enable-ai-tools/atoti-java-sdk/auto-explain/setup).

  ### Fixed

  * PIVOT-14236 Chat: Fixed filters being added without their members. Member validation now resolves members
    by their full name path, so the assistant reliably finds them in the cube.

  * PIVOT-14139 Visualize This: Added a dependency on the Spring AI Community `tool-search-tool` library
    (`org.springaicommunity:tool-search-tool`). On the Spring AI 1.1.x line, the Tool Search Tool advisor is not part
    of the core Spring AI release (it ships in Spring AI core from 2.0 onwards), so this community artifact is required
    to enable the feature.
</Update>

<Update label="6.1.22" description="2026-06-18">
  No changes were made since the last release.
</Update>

<Update label="6.1.21" description="2026-06-17">
  No changes were made since the last release.
</Update>

<Update label="6.1.20" description="2026-05-29">
  ### Added

  * PIVOT-12824 Auto-Explain: Added observability instrumentation. Auto-Explain now emits OpenTelemetry spans and metrics
    that cover request handling, recursive analysis and summary generation.
    See [Monitoring](../developer-guide/monitoring).
  * PIVOT-12824 Visualize This: Added observability instrumentation. The chat assistant now emits OpenTelemetry spans and
    metrics that cover conversation lifecycle, prompt execution and tool invocations.
    See [Monitoring](../developer-guide/monitoring).
  * PIVOT-12996 Auto-Explain: Exposed Auto-Explain as a Spring AI tool so it can be invoked from Visualize This as part of
    a chat conversation.
  * PIVOT-13680 Visualize This: AI cube descriptions now expose XMLA properties, and dimension, hierarchy and level
    descriptions are nested under their parent to give the model a structured view of the cube.
    See [How to configure Visualize This](../developer-guide/enable-ai-tools/atoti-java-sdk/chat/configuration).
  * PIVOT-13832 Added a customizable AI disclaimer that is returned with every AI response and displayed in the UI. A
    default disclaimer is provided when none is configured.
    See [Customize the AI disclaimer](../developer-guide/enable-ai-tools/atoti-java-sdk/disclaimer).
  * PIVOT-13978 MCP Server: Added an MCP credentials page in `starter-ai-mcp-server` that lets users mint and download
    tokens to connect MCP clients to the Atoti MCP server.
    See [MCP credentials page](../developer-guide/mcp-server/setup/mcp-credentials-page).
  * PIVOT-13970 MCP Server: Added self-issued OAuth 2.1 mode, where the Atoti server acts as its own authorization server.
    MCP clients (Claude Code, Claude Desktop, Cursor, ...) drive the browser-based PKCE flow against Atoti and users sign
    in with their existing Atoti credentials, with no external identity provider required. The browser PKCE flow includes a
    user consent page that requests approval before issuing an authorization code; the consent step can be disabled via
    `atoti.server.endpoint.mcp.oauth2.authserver.consent.enabled`.
    See [Configure self-issued OAuth 2.1](../developer-guide/mcp-server/setup/configure-oauth2-self-issued).

  ### Changed

  * Upgraded Spring AI to 1.1.6.
  * PIVOT-13970 MCP Server: The `starter-ai-mcp-server` now defaults the MCP transport to Streamable HTTP
    (`spring.ai.mcp.server.protocol=STREAMABLE`, served at `POST /mcp`) instead of the previous Server-Sent Events
    transport. If you rely on the SSE transport, restore it explicitly with `spring.ai.mcp.server.protocol: SSE`.
  * PIVOT-12494 AI license: When the license does not include the AI feature, Atoti now logs an informational message
    instead of throwing, so applications can start without AI features enabled.
  * PYTHON-826 Atoti Python SDK: `SessionConfig` now handles AI properties, allowing AI connection and chat options to be
    configured directly from Python.

  ### Removed

  * PIVOT-13932 Chat: Removed the legacy Chat v1 REST API and its associated payload types. Use the v2 streamable HTTP API
    instead.
</Update>

<Update label="6.1.19" description="2026-04-16">
  ### Added

  * Visualize This: The chat assistant now exposes the AI's reasoning process in real time. When the model reasons through
    a request before responding, the reasoning steps appear in the chat interface, giving visibility into how the
    assistant arrived at its answer.

  ### Changed

  * PIVOT-13553 Visualize This: Renamed the Spring Boot starter from `starter-ai-visualize-this` to `starter-ai-chat`.
    See [How to set up Visualize This](../developer-guide/enable-ai-tools/atoti-java-sdk/chat/setup) for the updated dependency.
  * PIVOT-13674 Visualize This: Possibility to add system prompt.
    See [How to configure Visualize This](../developer-guide/enable-ai-tools/atoti-java-sdk/chat/configuration)
  * PIVOT-13800 Auto-Explain: Updated the YAML configuration.
    See [How to configure Auto-Explain](../developer-guide/enable-ai-tools/atoti-java-sdk/auto-explain/configuration) for the
    updated configuration format.
</Update>
