mirror of
https://github.com/openai/codex.git
synced 2026-11-13 21:30:47 +00:00
Add recovery guidance to content-filter retries (#49119)
## Why Responses stopped by `content_filter` previously followed generic stream-error retry handling without guidance about the block. Retried requests need instructions to explain the limitation and offer a permitted alternative. ## What changed - Recognize content-filter failures as a distinct error while preserving retryability and the existing public error representation. - Append developer guidance to the conversation after each sampling block, retaining delivered output and using the existing retry handling. - Support a model catalog override through `model_messages.content_filter_guidance`. Missing, null, blank, or values exceeding 512 UTF-8 bytes fall back to bundled guidance. - The bundled guidance tells the model to avoid reproducing or working around blocked content, briefly explain the limitation, offer a permitted alternative, and continue unrelated authorized work. ## Testing Add a scenario and request-history snapshot covering repeated blocks, catalog guidance on each retry, retained partial output, and eventual completion. Add error-mapping assertions for retryability, public error classification, and error text. GitOrigin-RevId: ba0c201b3a5a3acf5cfa971332027240e0690225
This commit is contained in:
@@ -40,6 +40,7 @@ async fn codex_err_debug_preserves_legacy_shape() {
|
||||
fn retryability_preserves_error_details_distinctions() {
|
||||
let errors = [
|
||||
(CodexErr::ServerOverloaded, false),
|
||||
(CodexErr::new(CodexErrorDetails::ContentFilter), true),
|
||||
(
|
||||
CodexErr::new(CodexErrorDetails::RateLimitExceeded("retry later".into())),
|
||||
true,
|
||||
|
||||
Reference in New Issue
Block a user