`send_and_wait` resolves on a sub-agent's `session.idle` / `session.error`

Start in rust/src/session.rs at handle_notification and its send_and_wait waiter arm around lines 2256 and 2282-2304. Trace how agent_id is handled for session.idle, session.error, and assistant.message events. Add the regression test described in the issue: a child-tagged session.error must not resolve the parent wait, while a root session.idle must resolve it.

Repo/version: github/copilot-sdk, tag rust/v1.0.14 (e60d9037); CLI runtime 1.0.84-5.

Behaviour: A parent turn's send_and_wait returns early, with the wrong result, when a spawned sub-agent fails or goes idle.

Cause: handle_notification (rust/src/session.rs:2256; the waiter arm :2282-2304) takes the send_and_wait waiter on every session.idle / session.error and records every assistant.message as the wait's last message, with no agent_id check. The CLI's subagent bridge re-emits child events on the parent stream carrying the child's agent_id (the CLI runtime re-emits sub-agent events on the parent stream tagged with the child agent_id; session.error is among the re-emitted types), so a child's model-call failure resolves the parent's wait.

Fix shape: Only events with no agent_id (or equal to the root session's) may resolve the waiter or set its last message. Child-tagged idle/error/message events are ignored by the waiter (they still reach on_event).

Regression test: parent wait in flight; inject session.error with a child agent_id → wait NOT resolved; inject root session.idle → resolved.

Downstream: a consumer of this crate carries a local patch for this and cannot drop it until it is fixed upstream.