Introduce --oss flag to use gpt-oss models (#1848)

This adds support for easily running Codex backed by a local Ollama
instance running our new open source models. See
https://github.com/openai/gpt-oss for details.

If you pass in `--oss` you'll be prompted to install/launch ollama, and
it will automatically download the 20b model and attempt to use it.

We'll likely want to expand this with some options later to make the
experience smoother for users who can't run the 20b or want to run the
120b.

Co-authored-by: Michael Bolin <mbolin@openai.com>

codex-rs/core/src/config.rs

@@ -385,6 +385,8 @@ pub struct ConfigOverrides {
     pub codex_linux_sandbox_exe: Option<PathBuf>,
     pub base_instructions: Option<String>,
     pub include_plan_tool: Option<bool>,
+    pub default_disable_response_storage: Option<bool>,
+    pub default_show_raw_agent_reasoning: Option<bool>,
 }
 
 impl Config {
@@ -408,6 +410,8 @@ impl Config {
             codex_linux_sandbox_exe,
             base_instructions,
             include_plan_tool,
+            default_disable_response_storage,
+            default_show_raw_agent_reasoning,
         } = overrides;
 
         let config_profile = match config_profile_key.as_ref().or(cfg.profile.as_ref()) {
@@ -525,6 +529,7 @@ impl Config {
             disable_response_storage: config_profile
                 .disable_response_storage
                 .or(cfg.disable_response_storage)
+                .or(default_disable_response_storage)
                 .unwrap_or(false),
             notify: cfg.notify,
             user_instructions,
@@ -539,7 +544,10 @@ impl Config {
             codex_linux_sandbox_exe,
 
             hide_agent_reasoning: cfg.hide_agent_reasoning.unwrap_or(false),
-            show_raw_agent_reasoning: cfg.show_raw_agent_reasoning.unwrap_or(false),
+            show_raw_agent_reasoning: cfg
+                .show_raw_agent_reasoning
+                .or(default_show_raw_agent_reasoning)
+                .unwrap_or(false),
             model_reasoning_effort: config_profile
                 .model_reasoning_effort
                 .or(cfg.model_reasoning_effort)