> For the complete documentation index, see [llms.txt](https://docs.xenoraa.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.xenoraa.com/xenoraa-release-notes/v5.x-releases.md).

# v5.x Releases

## v5.x Release Series

> 2 releases in this series. Last updated: 2026-07-09 17:52 UTC

### v5.1.0 — Xena AI Phase 5 — Proactive Alert Chips on Dashboard

**Released:** 2026-07-06  |  **Category:** Xena AI  |  **Commit:** [`6a1b2c0`](https://github.com/goesscay/xenoraa/commit/6a1b2c0)

* New DB table: xena\_alert\_dismissals (user\_id, alert\_key, dismissed\_date — tracks per-day dismissals)
* New Model: XenaAlertDismissal with dismiss()/dismissedToday() static helpers
* XenaController: GET /admin/xena/alerts — reads today's snapshot alerts JSON, filters dismissed,
* transforms to {key, text, type, icon, action{label,url}} structured objects
* XenaController: POST /admin/xena/alerts/dismiss — saves dismissal for today
* Alert classification: crm (purple), activity (red), financial (amber), inventory (orange), general (blue)
* Routes: admin.xena.alerts (GET) + admin.xena.alerts.dismiss (POST)
* dashboard.blade.php: Xena Alerts bar between action buttons and CRM KPIs section
* (type-colored chips, icon, text, action button, dismiss x button)
* dashboard.blade.php: Phase 5 JS IIFE — fetches alerts on load, renders chips dynamically,
* dismiss with POST + fade-out animation, hides bar when all chips dismissed
* Verified: 3 alert chips visible (22 uncontacted leads, 2 overdue activities, 30% revenue drop)
* GitHub commit: 6a1b2c0

***

### v5.0.0 — Xena AI Phase 4 — xena\_tenant\_memory Persistent Memory Store

**Released:** 2026-07-06  |  **Category:** Xena AI  |  **Commit:** [`51b4cc8`](https://github.com/goesscay/xenoraa/commit/51b4cc8)

* New DB table: xena\_tenant\_memory (user\_id, category, memory\_key, memory\_value, source, context,
* confidence, times\_referenced, last\_referenced\_at)
* Categories: business\_info, preference, pattern, goal, product, team, financial, custom
* New Model: XenaTenantMemory with remember()/forget()/getForUser()/incrementRef() static helpers
* New Service: XenaMemoryService
* buildMemoryBlock(): formats all active memories as 'WHAT I KNOW ABOUT YOUR BUSINESS' section
* storeExplicit(): detects 'remember that X is Y' / 'remember my X is Y' patterns and saves
* checkForgetCommand(): detects 'forget that' / 'forget my X' and returns memory\_key to delete
* extractAndStore(): uses GPT to auto-extract new facts from each conversation turn
* XenaController: memory block injected into every system prompt as Layer 4 (after tenant profile,
* daily snapshot, platform knowledge)
* XenaController: after each assistant reply, runs memory extraction pipeline (non-blocking)
* Seeded 8 initial memories for gopi.blog: business\_name, business\_plan, primary\_module,
* lead\_sources\_active, lead\_creation\_method, pipeline\_stage\_focus, pipeline\_target, product\_count
* Verified: 'What do you know about my business and goals?' returns all seeded memories correctly
* GitHub commit: 51b4cc8

***


---

# 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 dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.xenoraa.com/xenoraa-release-notes/v5.x-releases.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.