feat: read model_provider and model_providers from config.toml (#853)

This is the first step in supporting other model providers in the Rust
CLI. Specifically, this PR adds support for the new entries in `Config`
and `ConfigOverrides` to specify a `ModelProviderInfo`, which is the
basic config needed for an LLM provider. This PR does not get us all the
way there yet because `client.rs` still categorically appends
`/responses` to the URL and expects the endpoint to support the OpenAI
Responses API. Will fix that next!

codex-rs/core/src/protocol.rs

@@ -11,6 +11,8 @@ use mcp_types::CallToolResult;
 use serde::Deserialize;
 use serde::Serialize;
 
+use crate::model_provider_info::ModelProviderInfo;
+
 /// Submission Queue Entry - requests from user
 #[derive(Debug, Clone, Deserialize, Serialize)]
 pub struct Submission {
@@ -27,6 +29,9 @@ pub struct Submission {
 pub enum Op {
     /// Configure the model session.
     ConfigureSession {
+        /// Provider identifier ("openai", "openrouter", ...).
+        provider: ModelProviderInfo,
+
         /// If not specified, server will use its default model.
         model: String,
         /// Model instructions