Add Arize tracing samples

[DABH]

Adds arize_tracing/, a sample that sends Temporal workflow traces to Arize Phoenix (self-hosted, one container) or Arize AX through the OpenTelemetry plugin, using the OpenInference conventions Arize renders. Companion to the Langfuse sample and to Arize's own Temporal guide.

Two scenarios share one telemetry module. ticket_triage/ keeps LLM calls in activities with the OpenInference OpenAI instrumentation, a custom span in workflow code, and a human approval via update. ticket_triage_agents/ runs the same flow on the OpenAI Agents SDK through OpenAIAgentsPlugin(use_otel_instrumentation=True). A small span processor gives Temporal's spans an OpenInference kind, sets the Arize session to the workflow ID, and records the activity attempt number.

verify_trace.py checks a trace through the Phoenix REST API: tree shape with span kinds, no spans with missing parents, enrichment attributes, LLM token usage, activity attempts, and no duplicates. The README runbook reproduces replay stress, worker restart, activity retry, worker crash mid-activity, and reset; every case was verified live against Phoenix with real model calls, and the screenshots come from those runs.

The agents scenario documents a known SDK issue (temporalio/sdk-python#1852): a worker that runs both the workflow and its activities in one process exports the temporal:startActivity spans with a missing parent. Its worker has --role workflows|activities to run them as separate processes, which avoids it.

Tests run without Phoenix, Docker, or an API key, including under the time-skipping environment.