Honor configured model defaults for spawned agents (#33631)

## What changed

- Apply `agents.default_subagent_model` and
  `agents.default_subagent_reasoning_effort` when a spawn request does not
  provide explicit values, including agent job workers.
- Allow full-history forks to use configured defaults or explicit model and
  reasoning-effort overrides while retaining the parent conversation context.
- Preserve the selected model and reasoning effort when an agent role does not
  override them.

## Testing

- Cover configured defaults, explicit override precedence, full-history forks,
  role application, and agent job workers.

GitOrigin-RevId: b1efa8c9abeee82355088fceef57560433144595

codex-rs/core/src/config/mod.rs

@@ -863,10 +863,10 @@ pub struct Config {
     /// User-configured maximum number of spawned agent threads per session.
     pub agent_max_threads: Option<usize>,
 
-    /// Reserved default model for spawned subagents.
+    /// Default model for spawned subagents when the spawn call does not select one.
     pub agent_default_subagent_model: Option<String>,
 
-    /// Reserved default reasoning effort for spawned subagents.
+    /// Default reasoning effort for spawned subagents when the spawn call does not select one.
     pub agent_default_subagent_reasoning_effort: Option<ReasoningEffort>,
 
     /// Maximum runtime in seconds for agent job workers before they are failed.