> 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/kodesage-release-notes-0.9.10.md).

# Kodesage Release Notes - 0.9.10

This release introduces the Discovery agent for automated UI mapping and integrates Klicker MCP for computer-use via the CLI. It also adds CLI change rollback auto Skill detection.

### **13 November 2026**

#### **New capabilities**

* **UI Discovery agent** – walk through the UI and its screens; Kodesage automatically creates a map of the application, later used as part of the Knowledge Base
* **Klicker MCP** – computer-use capability, shipped with the Kodesage CLI

#### **Improvements**

* **Concise agent prompt** – faster and more accurate answers
* **Better parsing and chunking for Magic applications** – Magic Oracle DDL is chunked per object, with procedures, tables and concepts linked
* **Roll back changes in the CLI** - restores the files the agent changed (/rewind)
* Agent Skills are automatically recognized in a repo and the model can select them
* PDF metadata is now ingested and searchable – users can ask about a PDF's properties
* Support for Oracle 11g version as direct DB connection
* Citations and section numbers are optional in Docs Studio exports;
* vLLM updated from 0.31.0 to 0.33.0
* Unified document attachments in the web UI and the CLI, support large PDF uploads

#### **Manual user todos**

* none

***


---

# 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/kodesage-release-notes-0.9.10.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.
