add web_search_cached flag (#8795)

Add `web_search_cached` feature to config. Enables `web_search` tool
with access only to cached/indexed results (see
[docs](https://platform.openai.com/docs/guides/tools-web-search#live-internet-access)).

This takes precedence over the existing `web_search_request`, which
continues to enable `web_search` over live results as it did before.

`web_search_cached` is disabled for review mode, as `web_search_request`
is.

codex-rs/core/src/features.rs

@@ -72,8 +72,11 @@ pub enum Feature {
     UnifiedExec,
     /// Include the freeform apply_patch tool.
     ApplyPatchFreeform,
-    /// Allow the model to request web searches.
+    /// Allow the model to request web searches that fetch live content.
     WebSearchRequest,
+    /// Allow the model to request web searches that fetch cached content.
+    /// Takes precedence over `WebSearchRequest`.
+    WebSearchCached,
     /// Gate the execpolicy enforcement for shell/unified exec.
     ExecPolicy,
     /// Enable Windows sandbox (restricted token) on Windows.
@@ -330,6 +333,12 @@ pub const FEATURES: &[FeatureSpec] = &[
         stage: Stage::Stable,
         default_enabled: false,
     },
+    FeatureSpec {
+        id: Feature::WebSearchCached,
+        key: "web_search_cached",
+        stage: Stage::Experimental,
+        default_enabled: false,
+    },
     // Beta program. Rendered in the `/experimental` menu for users.
     FeatureSpec {
         id: Feature::UnifiedExec,