Switch runtime to cloud config bundle (#24622)

## Summary

- Adapts the moved `codex-cloud-config` crate from the legacy cloud
requirements endpoint to the new config bundle endpoint.
- Switches runtime consumers from `CloudRequirementsLoader` to
`CloudConfigBundleLoader` so one shared bundle supplies cloud-delivered
config and requirements.
- Removes the legacy cloud requirements domain loader path.

## Details

This intentionally keeps `codex-cloud-config` monolithic for review
lineage: the previous PR establishes the crate move, and this PR shows
the behavior change against that moved implementation. A follow-up PR
splits the module back into focused files.

The new bundle path preserves the important cloud requirements loader
semantics where intended: account-scoped signed cache, 30 minute TTL, 5
minute refresh cadence, retry/backoff, auth recovery, and fail-closed
startup loading. The cached payload changes from a single requirements
TOML string to the backend-delivered bundle, and validation rejects
malformed config or requirements fragments before cache write/use.

codex-rs/backend-client/src/client.rs

@@ -1,6 +1,5 @@
 use crate::types::CodeTaskDetailsResponse;
 use crate::types::ConfigBundleResponse;
-use crate::types::ConfigFileResponse;
 use crate::types::PaginatedListTaskListItem;
 use crate::types::RateLimitReachedKind as BackendRateLimitReachedKind;
 use crate::types::RateLimitStatusPayload;
@@ -393,23 +392,6 @@ impl Client {
         self.decode_json::<TurnAttemptsSiblingTurnsResponse>(&url, &ct, &body)
     }
 
-    /// Fetch the managed requirements file from codex-backend.
-    ///
-    /// `GET /api/codex/config/requirements` (Codex API style) or
-    /// `GET /wham/config/requirements` (ChatGPT backend-api style).
-    pub async fn get_config_requirements_file(
-        &self,
-    ) -> std::result::Result<ConfigFileResponse, RequestError> {
-        let url = match self.path_style {
-            PathStyle::CodexApi => format!("{}/api/codex/config/requirements", self.base_url),
-            PathStyle::ChatGptApi => format!("{}/wham/config/requirements", self.base_url),
-        };
-        let req = self.http.get(&url).headers(self.headers());
-        let (body, ct) = self.exec_request_detailed(req, "GET", &url).await?;
-        self.decode_json::<ConfigFileResponse>(&url, &ct, &body)
-            .map_err(RequestError::from)
-    }
-
     /// Fetch the selected cloud-managed config bundle from codex-backend.
     ///
     /// `GET /api/codex/config/bundle` (Codex API style) or

codex-rs/backend-client/src/lib.rs

@@ -7,7 +7,6 @@ pub use client::RequestError;
 pub use types::CodeTaskDetailsResponse;
 pub use types::CodeTaskDetailsResponseExt;
 pub use types::ConfigBundleResponse;
-pub use types::ConfigFileResponse;
 pub use types::DeliveredConfigToml;
 pub use types::DeliveredRequirementsToml;
 pub use types::DeliveredTomlFragment;

codex-rs/backend-client/src/types.rs

@@ -1,5 +1,4 @@
 pub use codex_backend_openapi_models::models::ConfigBundleResponse;
-pub use codex_backend_openapi_models::models::ConfigFileResponse;
 pub use codex_backend_openapi_models::models::CreditStatusDetails;
 pub use codex_backend_openapi_models::models::DeliveredConfigToml;
 pub use codex_backend_openapi_models::models::DeliveredRequirementsToml;