core: surface terminal subagent errors to parent agents (#28375)

## Why

When a subagent exhausts its retries, it emits an `Error`, but the
generic task lifecycle then emits `TurnComplete(None)`. That completion
used to overwrite the subagent's `Errored` status with
`Completed(None)`, so the parent received an empty completion
notification.

This made a failed child look indistinguishable from a child that
completed without an answer. In unattended or long-running multi-agent
work, the root could silently continue without knowing that delegated
work failed or how to restart it.

## Behavior

Before, a terminal stream failure was reduced to an empty completion:

```text
<subagent_notification>
{"agent_path":"/root/worker","status":{"completed":null}}
</subagent_notification>
```

Now the parent receives the actual terminal error, bounded to 1,000
tokens, together with an actionable recovery hint:

```text
<subagent_notification>
{
  "agent_path": "/root/worker",
  "status": {
    "errored": "stream disconnected before completion: stream closed before response.completed"
  },
  "next_action": "This agent's turn failed. If you still need this agent, use `followup_task` to give it another task."
}
</subagent_notification>
```

The notification remains queue-only: it does not wake the root or replay
the failed request. The root sees it at the next sampling boundary and
can use `followup_task` to start a new turn for that agent.

## What changed

- Added terminal-error precedence to the [agent status
reducer](https://github.com/openai/codex/blob/e95fcfe2bb6a02f1a75650afa20048859f556511/codex-rs/core/src/agent/status.rs#L23-L34),
so a closing `TurnComplete` cannot erase an immediately preceding
`Errored` status.
- Made MultiAgentV2 completion forwarding use the retained session
status instead of re-deriving `Completed(None)` from the final event.
- Extended the [subagent notification
fragment](https://github.com/openai/codex/blob/e95fcfe2bb6a02f1a75650afa20048859f556511/codex-rs/core/src/context/subagent_notification.rs#L6-L60)
with a `next_action` for terminal errors and a hard cap on model-visible
error text.
- Kept successful completions and interrupted turns unchanged.

## Verification

- Added a status-reducer test proving that `Errored` survives the
trailing `TurnComplete`.
- Added an integration test that exhausts a subagent's stream retries
and verifies the exact `agent_message` delivered to the parent,
including the error and `followup_task` guidance.
- Re-ran the existing successful-completion and interrupted-turn
notification tests.

codex-rs/core/src/session/turn_context.rs

@@ -167,6 +167,7 @@ pub struct TurnContext {
     pub(crate) extension_data: Arc<codex_extension_api::ExtensionData>,
     pub(crate) turn_skills: TurnSkillsContext,
     pub(crate) turn_timing_state: Arc<TurnTimingState>,
+    pub(crate) terminal_error: Arc<Mutex<Option<String>>>,
     pub(crate) server_model_warning_emitted: AtomicBool,
     pub(crate) model_verification_emitted: AtomicBool,
 }
@@ -336,6 +337,7 @@ impl TurnContext {
             extension_data: Arc::clone(&self.extension_data),
             turn_skills: self.turn_skills.clone(),
             turn_timing_state: Arc::clone(&self.turn_timing_state),
+            terminal_error: Arc::clone(&self.terminal_error),
             server_model_warning_emitted: AtomicBool::new(
                 self.server_model_warning_emitted.load(Ordering::Relaxed),
             ),
@@ -639,6 +641,7 @@ impl Session {
             extension_data,
             turn_skills: TurnSkillsContext::new(skills_outcome),
             turn_timing_state: Arc::new(TurnTimingState::default()),
+            terminal_error: Arc::new(Mutex::new(None)),
             server_model_warning_emitted: AtomicBool::new(false),
             model_verification_emitted: AtomicBool::new(false),
         }