GenAI utils | Invoke Agent demo app

[etserend]

Description

Adds AgentInvocation type and agent() context manager to opentelemetry-util-genai, enabling instrumentation of agent invocation lifecycle events with OpenTelemetry spans following the GenAI agent semantic conventions.

This is the second in a series of PRs adding agent lifecycle telemetry (following create_agent in #4217).

Example trace output:

Trace (e71e16deb2ecd162e3f4fc67c240818b)
└── invoke_agent Currency Exchange Agent (4.16s, Client)
    ├── gen_ai.operation.name: invoke_agent
    ├── gen_ai.agent.name: Currency Exchange Agent
    ├── gen_ai.agent.description: Currency exchange agent demo
    ├── gen_ai.provider.name: gcp_vertex_ai
    ├── gen_ai.request.model: gemini-2.5-flash
    ├── gen_ai.response.finish_reasons: ["stop"]
    ├── gen_ai.usage.input_tokens: 12
    ├── gen_ai.usage.output_tokens: 87
    ├── server.address: us-central1-aiplatform.googleapis.com
    │
    └── chat gemini-2.5-flash (4.12s, Client)
        ├── gen_ai.operation.name: chat
        ├── gen_ai.system: vertex_ai
        ├── gen_ai.request.model: gemini-2.5-flash
        ├── gen_ai.response.model: gemini-2.5-flash
        ├── gen_ai.response.finish_reasons: ["stop"]
        ├── gen_ai.usage.input_tokens: 12
        ├── gen_ai.usage.output_tokens: 87
        ├── server.address: us-central1-aiplatform.googleapis.com
        └── server.port: 443