Add model and reasoning effort to MCP turn metadata (#21219)

## Why
- Similar change as https://github.com/openai/codex/pull/19473.
- Without change: MCP tool calls receive
`_meta["x-codex-turn-metadata"]` with `session_id`, `turn_id`, and
`turn_started_at_unix_ms`.
- Issue: MCP servers may want the model and reasoning effort to better
understand tool-call behavior and latency relative to turn start.

## What Changed
- With change: MCP turn metadata now includes `model` and
`reasoning_effort`, propagated in `_meta["x-codex-turn-metadata"]`.
- Normal `/responses` turn metadata headers are unchanged.

## Verification
- `codex-rs/core/src/mcp_tool_call_tests.rs`
- `codex-rs/core/src/turn_metadata_tests.rs`
- `codex-rs/core/tests/suite/search_tool.rs`

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

@@ -119,20 +119,21 @@ impl TurnContext {
         )
     }
 
-    pub(crate) fn effective_reasoning_effort_for_tracing(&self) -> String {
+    pub(crate) fn effective_reasoning_effort(&self) -> Option<ReasoningEffortConfig> {
         if self.model_info.supports_reasoning_summaries {
-            match self
-                .reasoning_effort
+            self.reasoning_effort
                 .or(self.model_info.default_reasoning_level)
-            {
-                Some(effort) => effort.to_string(),
-                None => "default".to_string(),
-            }
         } else {
-            "default".to_string()
+            None
         }
     }
 
+    pub(crate) fn effective_reasoning_effort_for_tracing(&self) -> String {
+        self.effective_reasoning_effort()
+            .map(|effort| effort.to_string())
+            .unwrap_or_else(|| "default".to_string())
+    }
+
     pub(crate) fn model_context_window(&self) -> Option<i64> {
         let effective_context_window_percent = self.model_info.effective_context_window_percent;
         self.model_info