Treat incomplete responses as terminal errors (#53451)

## Why

Incomplete responses such as `max_output_tokens` were classified as stream errors, allowing retries and compaction model fallback after the response had hit its output limit.

## What changed

Introduce `ResponseIncomplete` errors that preserve the server-provided reason and stop stream processing immediately. Make these errors non-retryable and stop compaction without falling back to the selected model. Record incomplete responses separately in sampler failure metrics.

## Testing

Add regression tests that verify incomplete responses surface a terminal error without retries over SSE and WebSocket, and that compaction stops without retrying or switching models for both local and remote compaction.

GitOrigin-RevId: 6e107d441b9bf03fa47ea47b88eeb94b71a9f729

codex-rs/codex-api/src/api_bridge.rs

@@ -29,6 +29,7 @@ pub fn map_api_error(err: ApiError) -> CodexErr {
         | ApiError::Api { .. }
         | ApiError::Stream(_)
         | ApiError::ContentFilter
+        | ApiError::ResponseIncomplete(_)
         | ApiError::ContextWindowExceeded
         | ApiError::QuotaExceeded
         | ApiError::UsageNotIncluded
@@ -58,6 +59,9 @@ fn map_api_error_details(err: ApiError) -> CodexErr {
         }
         ApiError::Stream(msg) => CodexErr::Stream(msg),
         ApiError::ContentFilter => CodexErr::new(CodexErrorDetails::ContentFilter),
+        ApiError::ResponseIncomplete(incomplete) => {
+            CodexErr::new(CodexErrorDetails::ResponseIncomplete(incomplete))
+        }
         ApiError::ServerOverloaded { .. } => CodexErr::ServerOverloaded,
         ApiError::FlexUnavailable => CodexErr::new(CodexErrorDetails::FlexUnavailable),
         ApiError::Api { status, message } => {