EPIC Goal

This epic covers the UI part of spike feature https://issues.redhat.com/browse/RHDHPLAN-849

Any backend work for the PoC should be covered by https://issues.redhat.com/browse/RHIDP-11566

What are we trying to solve here?

Our main goal is to ensure the technical feasibility of the deep context awareness mode for Lightspeed. The frontend part should be focusing on:

• The user is able to use the LS agent in docked and or overlay mode.
• The user is able to switch to the deep context awareness mode, thus this mode is not enabled by default.

Background/Feature Origin

The goal is to determine how to securely and effectively inject "screen context" into the LLM's prompt regardless of which UI mode is active, enabling the AI to provide directed advice without manual copy-pasting.

Why is this important?

The frontend / UI side is equally important for this feature as the deep context awareness mode requires a specific status of the agent and should enabled if conditions are met.

User Scenarios

N/A

Dependencies (internal and external)

• The backend PoC needs to be available first.

  Acceptance Criteria

• A frontend PoC is delivered.

Release Enablement/Demo - Provide necessary release enablement details
and documents

DEV - Upstream code and tests merged: <link to meaningful PR or GitHub
Issue>

DEV - Upstream documentation merged: <link to meaningful PR or GitHub
Issue>

DEV - Downstream build attached to advisory: <link to errata>

QE - Test plans in Playwright: <link or reference to playwright>

QE - Automated tests merged: <link or reference to automated tests>

DOC - Downstream documentation merged: <link to meaningful PR>