fix(runner): record why a turn-end provider restart failed

A failed turn-end restart was recovered silently: its cause surfaced only if
another turn started in the same run, which a single-turn run never does.
The executor now reports the cause once and the Runner records it as a
redacted runner diagnostic, so a kept instance shows why the restart failed.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

packages/paperclip-runner/runner/crates/runner-core/src/acpx_park_preparation.rs

@@ -48,6 +48,7 @@ impl AcpxCommandExecutor {
         // proven gone, then it is saved suspended, so the next run resumes the
         // same conversation instead of starting a new one.
         self.failed_turn_end_restart = Some(error.to_string());
+        self.unreported_turn_end_restart_failure = Some(error.to_string());
         self.recover_failed_generation_restart()
     }
 

packages/paperclip-runner/runner/crates/runner-core/src/acpx_provider_backend.rs

@@ -969,6 +969,8 @@ pub struct AcpxCommandExecutor {
     failed_turn_end_restart: Option<String>,
     /// The failed turn-end restart already failed a turn of this run closed.
     turn_end_restart_failed_turn: bool,
+    /// The failed turn-end restart's cause, until the Runner records it.
+    unreported_turn_end_restart_failure: Option<String>,
 }
 
 // The durable command's turn and the live provider callback have separate IDs.
@@ -1010,6 +1012,7 @@ impl AcpxCommandExecutor {
             recovery_pending_effects: None,
             failed_turn_end_restart: None,
             turn_end_restart_failed_turn: false,
+            unreported_turn_end_restart_failure: None,
             restore_error: None,
             persistence_error: None,
             #[cfg(test)]
@@ -2939,6 +2942,10 @@ impl CommandExecutor for AcpxCommandExecutor {
         self.restart_session_after_turn()
     }
 
+    fn take_turn_end_restart_failure(&mut self) -> Option<String> {
+        self.unreported_turn_end_restart_failure.take()
+    }
+
     fn execute(&mut self, command: &Command) -> Result<CommandExecution, DurableRunnerError> {
         self.restore()?;
         if self

packages/paperclip-runner/runner/crates/runner-core/src/durable/runner.rs

@@ -327,6 +327,12 @@ pub trait CommandExecutor {
         Ok(())
     }
 
+    /// The cause of a provider restart after a turn that failed and was
+    /// recovered, once; recorded as a runner diagnostic.
+    fn take_turn_end_restart_failure(&mut self) -> Option<String> {
+        None
+    }
+
     fn execute(&mut self, command: &Command) -> Result<CommandExecution, DurableRunnerError>;
 
     fn observe_recovery_state(&mut self, _state: &DurableState) -> Result<(), DurableRunnerError> {
@@ -2175,6 +2181,10 @@ fn poll_executor_events_after_controller_ack<E: CommandExecutor>(
     poll_executor_events(state, store, config, executor)?;
     if state.acked_source_seq >= state.highest_source_seq() {
         executor.prepare_next_turn()?;
+        if let Some(failure) = executor.take_turn_end_restart_failure() {
+            state.record_diagnostic(format!("turn-end provider restart failed: {failure}"));
+            store.save(state)?;
+        }
     }
     Ok(())
 }

packages/paperclip-runner/runner/crates/runner-core/src/native_provider_backend.rs

@@ -351,6 +351,13 @@ impl CommandExecutor for NativeProviderCommandExecutor {
         }
     }
 
+    fn take_turn_end_restart_failure(&mut self) -> Option<String> {
+        match self.selected.as_mut() {
+            Some(SelectedExecutor::Acpx(executor)) => executor.take_turn_end_restart_failure(),
+            _ => None,
+        }
+    }
+
     fn observe_recovery_state(
         &mut self,
         state: &crate::durable::DurableState,

packages/paperclip-runner/runner/crates/runner-core/tests/support/acpx_turn_end_restart.rs

@@ -356,6 +356,15 @@ fn the_next_run_resumes_the_conversation_after_a_failed_turn_end_restart() {
         harness.fixture.fault("reject-open");
         harness.executor.prepare_next_turn().unwrap();
         assert!(!alive(&old_pid));
+        // The Runner records the cause once as a diagnostic.
+        let reported = harness.executor.take_turn_end_restart_failure();
+        assert!(
+            reported
+                .as_deref()
+                .is_some_and(|cause| cause.contains("session.open")),
+            "{reported:?}"
+        );
+        assert_eq!(harness.executor.take_turn_end_restart_failure(), None);
         let saved = harness.fixture.state();
         assert_eq!(saved["lifecycle"], "suspended", "{saved}");
         assert_eq!(saved["providerExitUnconfirmed"], false);