docs(plan-task): clarify langfuse turn traces

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>

Author: MoveCloudROY

examples/e2e/plan_and_task/README.md

@@ -191,7 +191,9 @@ Install the optional extra before enabling Langfuse for this example:
 uv pip install -e ".[langfuse]"
 ```
 
-When `PLAN_TASK_LANGFUSE` is enabled, `main.py` calls `install_plan_task_langfuse_observability()` after `build_plan_task_world(...)` creates the `World` and before `Runner.run(...)` starts. The integration produces one trace per runner invocation and captures the plan interview, subagent/tool activity, LLM generations, retries, errors, context pressure, and completion scores through the shared EventBus-backed observability layer. Completed LLM, tool, and subagent observations preserve the ECS-recorded start and end timestamps when exported to Langfuse SDK v4, so the Langfuse UI reports the actual operation latency instead of the near-zero telemetry export duration.
+When `PLAN_TASK_LANGFUSE` is enabled, `main.py` calls `install_plan_task_langfuse_observability()` after `build_plan_task_world(...)` creates the `World` and before `Runner.run(...)` starts. In interactive mode, every `UserInputReceivedEvent` starts a `user.turn` trace that covers the complete chain from that user input until the next user input or process exit: prompt normalization, retrieval/compaction, LLM generations, tool calls, subagent spans, retries, errors, context pressure, and completion scores all stay inside that turn trace. One-shot runs without interactive input keep the runner trace for backward compatibility. Completed LLM, tool, and subagent observations preserve the ECS-recorded start and end timestamps when exported to Langfuse SDK v4, so the Langfuse UI reports the actual operation latency instead of the near-zero telemetry export duration.
+
+Subagents are exported as `subagent.<name>` spans inside the active `user.turn` trace. Their child-world LLM calls are exported as `generation` observations under that subagent span, and child-world tool/retrieval/API work is exported as child spans/events under the same turn trace rather than creating another top-level Langfuse trace. When a child-world generation requests a tool, that tool observation stays attached to the requesting generation so the Langfuse hierarchy shows the exact delegation chain.
 
 Use environment variables or a secret manager for `LANGFUSE_PUBLIC_KEY`, `LANGFUSE_SECRET_KEY`, and the Langfuse host value. Do not put concrete keys in scripts, docs, or command history. On exit, the CLI calls `flush()` and `shutdown()` on the observability handle so buffered trace events are sent before the process terminates.