feat: add Ollama agent with LlamaIndex and dynamic tool loading

[abhijeet-dhumal]

Depends and blocked by : #1, #2 and #3 resp.

Adds a local AI agent that drives the MCP server using Ollama-hosted models, with token-efficient tool discovery to avoid context overflow.

What's included:

• LlamaIndex FunctionAgent wired to the MCP server via Ollama LLM backend
• Two tool discovery modes selectable at startup:
  • Progressive — hierarchical phase-based lookup, loads only relevant tool schemas on demand
  • Semantic — embedding similarity search, finds tools by meaning without loading all schemas
• CLI entry point: kubeflow-mcp agent --model qwen3:8b --mode progressive

[google-oss-prow]

[APPROVALNOTIFIER] This PR is NOT APPROVED

This pull-request has been approved by:
Once this PR has been reviewed and has the lgtm label, please ask for approval from abhijeet-dhumal. For more information see the Kubernetes Code Review Process.

The full list of commands accepted by this bot can be found here.

Details

Needs approval from an approver in each of these files:

• OWNERS

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment