Expose MCP provenance to tool lifecycle extensions (#40976)

## What changed

- Add optional `McpToolContext` metadata to `ToolStartInput`, exposing the
  model-visible MCP tool details and its source classification without exposing
  the executable client.
- Classify MCP calls as connectors, configured servers, plugin servers,
  executor-selected plugins, or other registrations based on the prepared call.
- Prepare each MCP call before notifying tool lifecycle contributors and reuse
  that same call for execution so the callback describes the call that runs.

## Testing

- Cover host-owned connector calls and extension-owned Apps server calls,
  including their distinct provenance and executed tool names.

GitOrigin-RevId: efd23f511b1045ffdd96349d621ad62365569b2b

codex-rs/core/src/mcp_tool_call.rs

@@ -119,6 +119,7 @@ pub(crate) async fn handle_mcp_tool_call(
     call_id: String,
     originating_item_id: Option<ResponseItemId>,
     tool_info: &ToolInfo,
+    prepared_call: Option<PreparedMcpCall>,
     hook_tool_name: HookToolName,
     invocation_tool_name: ToolName,
     arguments: String,
@@ -149,7 +150,7 @@ pub(crate) async fn handle_mcp_tool_call(
         arguments: arguments_value.clone(),
     };
 
-    let Some(prepared_call) = sess.prepare_mcp_call(&server, &tool_name).await else {
+    let Some(prepared_call) = prepared_call else {
         let item_metadata =
             McpToolCallItemMetadata::from_tool_metadata(&server, /*metadata*/ None);
         let result = notify_mcp_tool_call_skip(