EPIC Goal

This EPIC focuses on the research work that is necessary around the "Deep Context" Retrieval feature for RHDH Lightspeed. This covers the backend part of the Deep Context Awareness feature (thus the retrieval term)

The main research action items are:

1. Investigate already existing solutions around deep context retrieval.
2. Investigate the technical aspect for the implementation (backend only).
3. Provide design documents for the suggested solution.

What are we trying to solve here?

In other words this EPIC tries to ensure the technical feasibility around the "Deep Context" awareness feature (backend side), by checking existing approaches, creating all necessary technical documents/designs.

Background/Feature Origin

From the parent feature: This EPIC aims to investigate the technical architecture required to share client-side RHDH context (e.g., the currently viewed Catalog Entity, TechDocs page, or Plugin state) with the Lightspeed backend during a chat session.

...

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 research phase of the Deep Context Awareness will help us understand the technical requirements and the challenges of this feature.

User Scenarios

N/A as this is just a collection of spikes

Dependencies (internal and external)

N/A

Acceptance Criteria

As mentioned in the feature description, the following documents need to be created:

• Technical Design Document
• List of limitations
• ROM estimate for implementation

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>