Add server selection UI for per-server LLM configuration

[Copilot]

The dashboard displayed all connected servers but always edited the first one's configuration. No UI existed to select which server to configure, making per-server LLM customization impossible despite backend support.

Changes

UI & Interaction

• Made server items clickable with data-server-id attribute
• Added .selected CSS class for visual feedback (blue border/background)
• Display selected server name in configuration header: "LLM Configuration (Server Name)"
• Added instructional text: "Click a server to view and edit its configuration"

JavaScript Logic

async function selectServer(serverId) {
    state.currentServerId = serverId;
    state.currentServerName = state.servers.find(s => s.id === serverId)?.name;
    
    // Update visual selection
    document.querySelectorAll('.server-item').forEach(item => {
        item.classList.toggle('selected', item.getAttribute('data-server-id') === serverId);
    });
    
    updateServerNameDisplay();
    await loadConfig();  // Fetch selected server's config
}

State Management

• Added currentServerName and servers to state object
• Persist selection across page refreshes
• Default to first server if previous selection no longer exists

Screenshots

Gaming Community selected (OpenAI GPT-4):

Dev Team selected (Anthropic Claude):

Testing

Added tests/test_server_config.py verifying:

• Configuration isolation (updates to server A don't affect server B)
• Each server can have independent provider/model/prompt/temperature
• Database-level separation

Original prompt

---

This section details on the original issue you should resolve

<issue_title>per server llm configuration does not work</issue_title>
<issue_description>currently there is no way to configure what llm you use, the context window, and the system prompt per server the bot is in

by default updating the system prompt updates updates it in the sever DB, even though there is not a way to choose which server you are editing</issue_description>

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

• Fixes per server llm configuration does not work #4

---

💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.