Add OpenTelemetry observability support

[pcomans]

Summary

Add OpenTelemetry-based observability to RubyLLM, enabling users to send traces to any compatible backend (LangSmith, Honeycomb, New Relic, etc.).

Follows the OpenTelemetry Semantic Conventions for GenAI.

What's Included

• Chat completion tracing: chat {model_id} spans (e.g., chat gpt-4o) with model, provider, token counts, and GenAI semantic convention attributes
• Streaming support: Single span wraps entire streaming operation; token counts and content recorded on completion
• Tool call tracing: execute_tool {tool_name} child spans (e.g., execute_tool get_weather) with tool name, arguments, and results
• Session tracking: UUID per Chat instance for grouping multi-turn conversations. ActiveRecord chats use namespaced record IDs (ClassName:id) to prevent collisions across models
• Custom metadata: Attach arbitrary metadata via chat.with_metadata(user_id: 123) for filtering/debugging. Native types (int, float, bool) preserved for better backend filtering
• Content logging: Opt-in prompt/completion logging with configurable truncation
• LangSmith compatibility: Optional tracing_langsmith_compat mode adds LangSmith-specific attributes (langsmith.span.kind, input.value/output.value panels)
• Config scoping: Tracing respects per-context configuration when using RubyLLM.context
• Fail-fast validation: Raises ConfigurationError with helpful message if tracing enabled but OpenTelemetry gems not installed
• NullTracer pattern: Minimal overhead when tracing disabled

Configuration

RubyLLM.configure do |config|
  config.tracing_enabled = true                  # Explicit opt-in required
  config.tracing_log_content = true              # Log prompts/completions (default: false)
  config.tracing_max_content_length = 10_000     # Truncation limit (default: 10000)
  config.tracing_langsmith_compat = true         # Add LangSmith-specific attributes (auto-sets metadata prefix)
end

Not in Scope

Intentionally deferred to keep this PR focused:

• Other operations (embed, paint, transcribe, moderate): Lower priority; can add incrementally based on demand

[pcomans]

@crmne I'd love to get this merged. Let me know how I can support you.

[patriciomacadden]

I really like OpenTelemetry and i think something like this is super helpful. But I think the instrumentation belongs somewhere else. OpenTelemetry instruments rails (active record, action view, action mailers, etc), sidekiq, sinatra, rake, etc, and the instrumentation code doesn't live in the original code. The instrumentation code is installed separately and configured separately. See how OpenTelemetry instruments various libraries.

I think the right approach is to follow OpenTelemetry's approach. This way it will be consistent with OpenTelemetry, and it will keep RubyLLM clean, free of OpenTelemetry code.