> For the complete documentation index, see [llms.txt](https://docs.kodesage.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.kodesage.ai/release-notes/whats-new-in-0.8.x/kodesage-release-notes-0.8.4.md).

# Kodesage Release Notes - 0.8.4

File uploads in chat, researcher and explorer agents, PostgreSQL data sources, and a faster knowledge base.

### **28 April 2026**

#### **💬 Ask**

* File uploads in chat, with an allowed file-type policy.
* New researcher and explorer agents, plus a file toolkit.
* Wiki and Confluence references now resolve against canonical knowledge-base sources.
* Faster reference loading.
* Configurable reasoning effort for answers.

***

#### **📄 Docs Studio**

* A loader while data sources are still loading.
* Fixed stray formatting in generated content.
* A simpler, more predictable generation engine.

***

#### **⚙️ Settings**

* Removed unused settings and dead configuration.

***

#### **⌨️ CLI**

* Completion is validated before the interactive agent loop exits.

***

#### **🔧 Platform & Performance**

* PostgreSQL added as a database data source, on a unified connection model.
* Confluence incremental sync now catches same-day edits.
* The knowledge-base service has been rewritten for performance.
* Model download integrity checks prevent corrupt weights breaking startup.
* Improved table handling and styling in document export.
* Worker isolation and cross-process cancellation in ingestion.


---

# 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.kodesage.ai/release-notes/whats-new-in-0.8.x/kodesage-release-notes-0.8.4.md?ask=<question>&goal=<user_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.
