Use issuing step settings for approval decisions (#40821)

## Why

Tool actions and approval retries can outlive the step that issued them. If approval handling reads newer turn settings, a delayed action can use the wrong approval policy or reviewer.

## What changed

- Capture the approval policy and reviewer in `GuardianReviewContext` from the issuing step.
- Use step settings for command, patch, permission, sandbox-retry, and remote-network approval decisions.
- Use the active task's published settings for background network approvals and long-lived Unix shell interception.
- Preserve explicit MCP reviewer overrides.

## Testing

Added regression coverage for permission requests, same-turn network policy changes, delayed commands after a new turn starts, sandbox retries, patch policy selection, and MCP reviewer overrides.

GitOrigin-RevId: b7e84a2e1e79a71502272b15b5ef5b0e5643f8b0

codex-rs/core/src/unified_exec/process_manager.rs

@@ -1266,7 +1266,7 @@ impl UnifiedExecProcessManager {
             .create_exec_approval_requirement_for_shell(
                 ExecApprovalRequest {
                     command: &request.command,
-                    approval_policy: turn.approval_policy(),
+                    approval_policy: context.step_context.settings.approval_policy(),
                     permission_profile: request.turn_environment.permission_profile().clone(),
                     environment_policy: request.turn_environment.config().exec_policy.as_ref(),
                     windows_sandbox_level: request.turn_environment.config().windows_sandbox_level,
@@ -1311,7 +1311,7 @@ impl UnifiedExecProcessManager {
             tool_name: ToolName::plain("exec_command"),
         };
         orchestrator
-            .run(&mut runtime, &req, &tool_ctx, turn, turn.approval_policy())
+            .run(&mut runtime, &req, &tool_ctx)
             .await
             .map(|result| (result.output, result.deferred_network_approval))
             .map_err(|err| match err {