Clarify workspace discovery model in README

[Copilot]

Users expected to create workspaces in the application itself, but Gennie-X discovers existing workspaces from AI agent local storage (VS Code/Cursor/Claude Code). This fundamental concept was not explicitly stated.

Changes

• Added "Understanding Workspaces" section (lines 55-63) positioned before Basic Usage
  • States upfront that workspaces are discovered, not created
  • Provides 4-step workflow: use agent → open project → chat with AI → storage auto-detected
  • Complements existing troubleshooting sections (lines 87, 118) and config documentation

The section appears immediately after Installation, establishing the discovery model before users attempt to use the tool.

### Understanding Workspaces

**Important:** Gennie-X does **not** create workspaces. Instead, it *discovers* 
existing workspaces from your AI coding agents (VS Code/Cursor/Claude Code). 
The tool reads the local storage where these agents save their conversation history.

To have workspaces available:
1. Use one of the supported agents (GitHub Copilot in VS Code, Cursor, or Claude Code)
2. Open a project/folder in the agent
3. Start at least one chat conversation with the AI assistant
4. The agent will save this data to its local storage (auto-detected by Gennie-X)

Warning

Firewall rules blocked me from connecting to one or more addresses (expand for details)

I tried to connect to the following addresses, but was blocked by firewall rules:

• astral.sh
  • Triggering command: /usr/bin/curl curl -LsSf REDACTED (dns block)

If you need me to access, download, or install something from one of these locations, you can either:

• Configure Actions setup steps to set up my environment, which run before the firewall is enabled
• Add the appropriate URLs or hosts to the custom allowlist in this repository's Copilot coding agent settings (admins only)

Original prompt

---

This section details on the original issue you should resolve

<issue_title>Using this tool - creating workspaces</issue_title>
<issue_description>It's not clear how to create a workspace.

uv run python run_cli.py --extract --all --agent cursor --run-dir C:\Users\username\Documents\GitHub\kg-data-processor
Warning: Failed to read logging config: Config file not found: config\config.yaml
[INFO] Filtered to 0 workspaces with agent 'cursor'
[INFO] Extracting all 0 workspaces from storage
[ERROR] No workspaces to process
[TIP] Use --list to see available workspaces

C:\Users\alombardi\Documents\GitHub\gennie-x>uv run python run_cli.py --list
Warning: Failed to read logging config: Config file not found: config\config.yaml

Available workspaces (page 1, showing 0 of 0):

ID                                       Name                           Agent      Sessions
------------------------------------------------------------------------------------------

More detailed instructions in readme would be beneficial.</issue_description>

<agent_instructions>verify the fix and close</agent_instructions>

Comments on the Issue (you are @copilot in this section)

@hosamsh Thanks for the report. The README was missing a config step to setup the configuration file. You can copy or rename config/config.example.yaml to config.yaml before running the CLI/web. You don't need to create a workspace in the app itself; it reads existing VS Code/Cursor/Claude Code workspaces from the agent's local storage.

After copying the config file, run:
uv run python run_cli.py --list.

If it still shows 0, open any workspace in the one of these agents (Code/Cursor/CC), and start a chat once so local storage is created, or set extract..workspace_storage in config to the correct folder.</comment_new>

• Fixes Using this tool - creating workspaces #1

---

✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.

[Copilot]

Pull request overview

This PR addresses user confusion about workspace creation by adding a new "Understanding Workspaces" section to the README. The issue arose because users expected to create workspaces within Gennie-X itself, but the tool actually discovers existing workspaces from AI coding agents' local storage (VS Code/Cursor/Claude Code). This fundamental concept was not explicitly documented, leading to confusion when users encountered empty workspace lists.

Changes:

• Added "Understanding Workspaces" section positioned immediately after Installation and before Basic Usage
• Explicitly states that Gennie-X discovers (not creates) workspaces from AI agent local storage
• Provides a clear 4-step workflow for users to ensure workspaces are available