Implement elicitation and sampling for Kusto cluster and database selection

[Copilot]

This PR implements intelligent parameter elicitation and sampling functionality for Kusto operations when cluster URIs or databases are unclear or missing.

Problem

Previously, all Kusto operations required explicit cluster_uri and database parameters. When these were missing or unclear, users would get generic error messages without guidance on available options or intelligent defaults.

Solution

Added a comprehensive elicitation and sampling system that:

🎯 Elicitation: Provides helpful guidance when parameters are missing

# Before: Generic error
kusto_query("StormEvents | take 5", None)  # TypeError

# After: Helpful guidance with available options
kusto_query_with_elicitation("StormEvents | take 5")
# KustoElicitationError: No cluster URI provided. Available clusters: 
# 'https://prod.kusto.windows.net', 'https://samples.kusto.windows.net'

🧠 Sampling: Intelligent parameter selection based on context

# Context-aware cluster selection
kusto_query_with_elicitation("show me sample data")  # Prefers clusters with "sample" in description

# Database inference from query content  
kusto_query_with_elicitation("TestDB.MyTable | take 10")  # Prefers "TestDB" database

Key Features

• New Exception Classes: KustoElicitationError provides structured information for user prompting
• Context-Based Sampling: Analyzes query content to make intelligent parameter choices
• Graceful Fallbacks: Tries sampling first, then elicitation if needed
• Rich Error Messages: Lists available options and suggests specific values
• Backward Compatibility: Existing functions unchanged

New Tools

• kusto_query_with_elicitation(): Execute queries with parameter elicitation support
• kusto_sample_data_with_elicitation(): Sample table data with parameter elicitation
• kusto_explore_with_elicitation(): Explore databases with parameter elicitation

Implementation Details

The system handles both scenarios from the issue:

1. Missing cluster/database: Elicits user interaction with helpful guidance
2. Multiple options available: Uses context-based sampling to intelligently pick one

Sampling logic includes:

• Query content analysis (e.g., "sample" queries → sample clusters)
• Database name hints (e.g., "DB.Table" → DB database)
• Default service preferences
• Random sampling as fallback

Testing

Added 18 comprehensive tests covering:

• Cluster sampling with various scenarios
• Database sampling with context awareness
• Elicitation error handling
• Tool function integration
• Edge cases and error conditions

All existing tests continue to pass, ensuring backward compatibility.

Fixes #54.

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:

• demo.kusto.windows.net
  • Triggering command: python manual_test_elicitation.py (dns block)
• production.kusto.windows.net
  • Triggering command: python manual_test_elicitation.py (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)

---

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