Add support for OTel GenAI Semantic Convention patterns in LLO handler

[mxiamxia]

Description of changes:
Handle specific span events by recognizing them via event.name. Move their associated attributes into Log events (as content) and remove them from the original Span Event.

• gen_ai.assistant.message (output)
• gen_ai.tool.message (input)
• gen_ai.user.message (input)
• gen_ai.system.message (input)
• gen_ai.choice (output)

Test

{
    "resource": {
        "attributes": {
            "aws.local.service": "langgraph-min",
            "aws.service.type": "gen_ai_agent",
            "telemetry.sdk.language": "python",
            "service.name": "langgraph-min",
            "cloud.resource_id": "fastapi-app",
            "aws.log.group.names": "test_trace-min-4",
            "telemetry.sdk.version": "1.33.1",
            "telemetry.auto.version": "0.11.0.dev0-aws",
            "telemetry.sdk.name": "opentelemetry"
        }
    },
    "scope": {
        "name": "strands.telemetry.tracer"
    },
    "timeUnixNano": 1756004845660372000,
    "observedTimeUnixNano": 1756004845662834000,
    "severityNumber": 9,
    "severityText": "",
    "body": {
        "output": {
            "messages": [
                {
                    "content": {
                        "message": "# Weather Forecast for New York City 🌤️\n\nHere's the current weather forecast for New York City (Manhattan area):\n\n## **Current Conditions (Tonight - Saturday Night, Aug 23)**\n🌙 **Tonight**: Partly Cloudy  \n- **Temperature**: Low around 70°F  \n- **Wind**: South 7-13 mph  \n- **Precipitation**: 0% chance  \n\n## **This Weekend**\n\n### **Sunday (Aug 24)**\n🌤️ **Partly Sunny**  \n- **High**: 77°F  \n- **Wind**: South 7-16 mph  \n- **Precipitation**: 10% chance  \n\n### **Sunday Night**  \n🌧️ **Chance Rain Showers** (after 8pm)  \n- **Low**: 72°F  \n- **Wind**: South 6-15 mph  \n- **Precipitation**: 40% chance  \n\n### **Monday (Aug 25)**  \n🌦️ **Chance Rain Showers**  \n- **High**: 80°F  \n- **Wind**: Southwest 6-10 mph  \n- **Precipitation**: 40% chance  \n\n## **Looking Ahead (Tuesday - Saturday)**\n\n**Tuesday**: ☀️ Sunny, High 76°F - Beautiful day!  \n**Wednesday**: 🌤️ Mostly Sunny, High 73°F  \n**Thursday**: 🌤️ Mostly Sunny, High 76°F  \n**Friday**: 🌤️ Mostly Sunny, High 76°F  \n**Saturday**: 🌤️ Mostly Sunny, High 75°F  \n\n## **Key Highlights**\n- **Pleasant temperatures** in the mid-70s to near 80°F\n- **Possible rain** Sunday night through Monday morning\n- **Great weather** returning Tuesday with sunny skies\n- **Comfortable humidity** levels expected\n- **Light to moderate winds** throughout the period\n\nThis forecast shows typical late August weather for NYC with comfortable temperatures and mostly pleasant conditions, with just a brief chance of showers early in the week before clearing up nicely!\n",
                        "finish_reason": "end_turn"
                    },
                    "role": "assistant"
                }
            ]
        },
        "input": {
            "messages": [
                {
                    "content": "You are a weather assistant with HTTP capabilities. You can:\n\n1. Make HTTP requests to the National Weather Service API\n2. Process and display weather forecast data\n3. Provide weather information for locations in the United States\n\nWhen retrieving weather information:\n1. First get the coordinates or grid information using https://api.weather.gov/points/{latitude},{longitude} or https://api.weather.gov/points/{zipcode}\n2. Then use the returned forecast URL to get the actual forecast\n\nWhen displaying responses:\n- Format weather data in a human-readable way\n- Highlight important information like temperature, precipitation, and alerts\n- Handle errors appropriately\n- Convert technical terms to user-friendly language\n\nAlways explain the weather conditions clearly and provide context for the forecast.\n",
                    "role": "system"
                },
                {
                    "content": {
                        "content": "[{\"text\": \"What is the weather in New York?\"}]"
                    },
                    "role": "user"
                }
            ]
        }
    },
    "attributes": {
        "event.name": "strands.telemetry.tracer"
    },
    "flags": 1,
    "traceId": "68aa81cd356fb8ea277cca6fbd34640d",
    "spanId": "5a3802fa510a2725"
}

By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.

[yiyuan-he]

LGTM