Treat inference hook denials as terminal errors (#60511)

## Why

An explicit denial from a workspace inference hook should stop the request, including retries and compaction model fallback.

## What changed

Recognize `inference_hook_denied` provider errors and preserve the provider's message, with a fallback when none is supplied. Expose the distinct `inferenceHookDenied` error through the app-server protocol and generated schemas and SDK types. Treat the denial as non-retryable during turns, compaction, and guardian review.

## Testing

Add coverage for terminal denials over HTTP, SSE, and WebSocket, error serialization and persistence in `thread/read`, and compaction failures that preserve token usage and history without retrying or falling back to another model.

GitOrigin-RevId: 2ebd480f01e52f4e6bd3db8a0f92d5814d18ccb1

codex-rs/codex-api/src/error.rs

@@ -57,6 +57,8 @@ pub enum ApiError {
     #[error("invalid prompt: {message}")]
     InvalidPrompt { message: String },
     #[error("{message}")]
+    InferenceHookDenied { message: String },
+    #[error("{message}")]
     ContentPolicyViolation {
         message: String,
         status: Option<StatusCode>,
@@ -96,6 +98,13 @@ pub(crate) fn parse_terminal_provider_error(
         .and_then(Value::as_str)
         .filter(|message| !message.trim().is_empty());
     match (code, status) {
+        ("inference_hook_denied", None | Some(StatusCode::FORBIDDEN)) => {
+            Some(ApiError::InferenceHookDenied {
+                message: message
+                    .unwrap_or("Your workspace inference hook blocked this request.")
+                    .to_owned(),
+            })
+        }
         ("context_length_exceeded", None | Some(StatusCode::BAD_REQUEST)) => {
             Some(ApiError::ContextWindowExceeded)
         }