Add under-development original-resolution view_image support (#13050)

## Summary

Add original-resolution support for `view_image` behind the
under-development `view_image_original_resolution` feature flag.

When the flag is enabled and the target model is `gpt-5.3-codex` or
newer, `view_image` now preserves original PNG/JPEG/WebP bytes and sends
`detail: "original"` to the Responses API instead of using the legacy
resize/compress path.

## What changed

- Added `view_image_original_resolution` as an under-development feature
flag.
- Added `ImageDetail` to the protocol models and support for serializing
`detail: "original"` on tool-returned images.
- Added `PromptImageMode::Original` to `codex-utils-image`.
  - Preserves original PNG/JPEG/WebP bytes.
  - Keeps legacy behavior for the resize path.
- Updated `view_image` to:
- use the shared `local_image_content_items_with_label_number(...)`
helper in both code paths
  - select original-resolution mode only when:
    - the feature flag is enabled, and
    - the model slug parses as `gpt-5.3-codex` or newer
- Kept local user image attachments on the existing resize path; this
change is specific to `view_image`.
- Updated history/image accounting so only `detail: "original"` images
use the docs-based GPT-5 image cost calculation; legacy images still use
the old fixed estimate.
- Added JS REPL guidance, gated on the same feature flag, to prefer JPEG
at 85% quality unless lossless is required, while still allowing other
formats when explicitly requested.
- Updated tests and helper code that construct
`FunctionCallOutputContentItem::InputImage` to carry the new `detail`
field.

## Behavior

### Feature off
- `view_image` keeps the existing resize/re-encode behavior.
- History estimation keeps the existing fixed-cost heuristic.

### Feature on + `gpt-5.3-codex+`
- `view_image` sends original-resolution images with `detail:
"original"`.
- PNG/JPEG/WebP source bytes are preserved when possible.
- History estimation uses the GPT-5 docs-based image-cost calculation
for those `detail: "original"` images.


#### [git stack](https://github.com/magus/git-stack-cli)
- 👉 `1` https://github.com/openai/codex/pull/13050
- ⏳ `2` https://github.com/openai/codex/pull/13331
- ⏳ `3` https://github.com/openai/codex/pull/13049

codex-rs/core/src/models_manager/manager.rs

@@ -471,6 +471,7 @@ mod tests {
             "apply_patch_tool_type": null,
             "truncation_policy": {"mode": "bytes", "limit": 10_000},
             "supports_parallel_tool_calls": false,
+            "supports_image_detail_original": false,
             "context_window": 272_000,
             "experimental_supported_tools": [],
         }))
@@ -549,6 +550,8 @@ mod tests {
             .build()
             .await
             .expect("load default test config");
+        let mut overlay = remote_model("gpt-overlay", "Overlay", 0);
+        overlay.supports_image_detail_original = true;
 
         let auth_manager =
             AuthManager::from_auth_for_testing(CodexAuth::from_api_key("Test API Key"));
@@ -556,7 +559,7 @@ mod tests {
             codex_home.path().to_path_buf(),
             auth_manager,
             Some(ModelsResponse {
-                models: vec![remote_model("gpt-overlay", "Overlay", 0)],
+                models: vec![overlay],
             }),
             CollaborationModesConfig::default(),
         );
@@ -568,6 +571,7 @@ mod tests {
         assert_eq!(model_info.slug, "gpt-overlay-experiment");
         assert_eq!(model_info.display_name, "Overlay");
         assert_eq!(model_info.context_window, Some(272_000));
+        assert!(model_info.supports_image_detail_original);
         assert!(!model_info.supports_parallel_tool_calls);
         assert!(!model_info.used_fallback_model_metadata);
     }
@@ -580,26 +584,24 @@ mod tests {
             .build()
             .await
             .expect("load default test config");
+        let mut remote = remote_model("gpt-image", "Image", 0);
+        remote.supports_image_detail_original = true;
         let auth_manager =
             AuthManager::from_auth_for_testing(CodexAuth::from_api_key("Test API Key"));
         let manager = ModelsManager::new(
             codex_home.path().to_path_buf(),
             auth_manager,
-            None,
+            Some(ModelsResponse {
+                models: vec![remote],
+            }),
             CollaborationModesConfig::default(),
         );
-        let known_slug = manager
-            .get_remote_models()
-            .await
-            .first()
-            .expect("bundled models should include at least one model")
-            .slug
-            .clone();
-        let namespaced_model = format!("custom/{known_slug}");
+        let namespaced_model = "custom/gpt-image".to_string();
 
         let model_info = manager.get_model_info(&namespaced_model, &config).await;
 
         assert_eq!(model_info.slug, namespaced_model);
+        assert!(model_info.supports_image_detail_original);
         assert!(!model_info.used_fallback_model_metadata);
     }
 

codex-rs/core/src/models_manager/model_info.rs

@@ -80,6 +80,7 @@ pub(crate) fn model_info_from_slug(slug: &str) -> ModelInfo {
         apply_patch_tool_type: None,
         truncation_policy: TruncationPolicyConfig::bytes(10_000),
         supports_parallel_tool_calls: false,
+        supports_image_detail_original: false,
         context_window: Some(272_000),
         auto_compact_token_limit: None,
         effective_context_window_percent: 95,