> For the complete documentation index, see [llms.txt](https://docs.datasaur.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.datasaur.ai/compatibility-and-updates/release-notes/version-6/6.171.0.md).
# 6.171.0
August 13, 2026
## **What's New? 💡**
### **Data Studio**
* Audio Labeling:
* [Timestamp labels can now be looped](https://docs.datasaur.ai/data-studio-projects/nlp-task-types/span-based/audio-project#loop-a-timestamp-label), making it easier to repeatedly listen to a specific audio segment.
* Added snap-to-grid when drawing timestamp labels, making it easier to align labels precisely without gaps or overlap.
* Metadata Extension — Added [personalized metadata pinning](https://docs.datasaur.ai/advanced/extensions/metadata#personalize-pinned-metadata), allowing each user to save their own pinned metadata preferences.
* Advanced Search in Span Labeling — Improved result ordering to remain consistent across files, even after refreshing or switching between files.
## **Bug Fixes 🐞**
### **Data Studio**
* Fixed an issue where users could not join a workspace through an invitation link.
* Fixed an issue where audio file previews could fail to load correctly in the Add Documents wizard.
* Fixed an issue in Span Labeling where pinned image, audio, and HTML metadata did not appear correctly in the editor.
### **LLM Labs**
* Fixed an issue in Knowledge Base where synced URL document activity showed a raw translation key instead of a user-facing message.
* Fixed an issue in Knowledge Base Activity where hovering over the Google Drive icon showed untranslated copy instead of a human-readable label.
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.
Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:
```
GET https://docs.datasaur.ai/compatibility-and-updates/release-notes/version-6/6.171.0.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.