[codex] Forward turn moderation metadata through app-server (#25710)

## Why
First-party backends can supply turn-scoped moderation metadata that
app-server clients need for client-side presentation. Exposing this as
an experimental typed notification lets opted-in clients consume it
without interpreting raw Responses API events.

## What changed
- forward `response.metadata.openai_chatgpt_moderation_metadata` from
Responses API SSE and WebSocket streams as turn-scoped moderation
metadata
- emit the experimental app-server v2 `turn/moderationMetadata`
notification with `{ threadId, turnId, metadata }`
- add app-server integration coverage for the typed moderation metadata
notification

## Testing
- `just test -p codex-core
build_ws_client_metadata_includes_window_lineage_and_turn_metadata`
- `just test -p codex-core` (fails locally: 46 failures and 1 timeout,
primarily missing `test_stdio_server` and shell snapshot timeouts)
- `just test -p codex-app-server-protocol`
- `just test -p codex-app-server
turn_moderation_metadata_emits_typed_notification_v2`
- `just test -p codex-app-server` (fails locally: 792 passed, 10 failed,
and 5 timed out; failures are in existing environment-sensitive tests,
primarily because nested macOS `sandbox-exec` is not permitted)
- `just write-app-server-schema --experimental --schema-root
/tmp/codex-app-server-schema-experimental`
This commit is contained in:
carlc-oai
2026-06-05 02:41:06 -07:00
committed by GitHub
Unverified
parent 6dc28ba6e0
commit 55aa071b17
26 changed files with 395 additions and 2 deletions
+3
View File
@@ -6,6 +6,7 @@ use codex_protocol::openai_models::ReasoningEffort as ReasoningEffortConfig;
use codex_protocol::protocol::ModelVerification;
use codex_protocol::protocol::RateLimitSnapshot;
use codex_protocol::protocol::TokenUsage;
use codex_protocol::protocol::TurnModerationMetadataEvent;
use codex_protocol::protocol::W3cTraceContext;
use futures::Stream;
use serde::Deserialize;
@@ -78,6 +79,8 @@ pub enum ResponseEvent {
ServerModel(String),
/// Emitted when the server recommends additional account verification.
ModelVerifications(Vec<ModelVerification>),
/// Emitted when the server includes moderation metadata for first-party turn presentation.
TurnModerationMetadata(TurnModerationMetadataEvent),
/// Emitted when `X-Reasoning-Included: true` is present on the response,
/// meaning the server already accounted for past reasoning tokens and the
/// client should not re-estimate them.