feat(gateway): complete OpenAI Responses WebSocket mode

.github/workflows/rust-ci.yml

@@ -387,11 +387,11 @@ jobs:
       - name: Setup sccache
         uses: mozilla-actions/sccache-action@v0.0.9
 
-      - name: Test scenario binaries
+      - name: Test scenario binaries and end-to-end suites
         env:
           RUSTC_WRAPPER: sccache
           SCCACHE_GHA_ENABLED: "true"
-        run: cargo test -p aether-integration-tests --bins
+        run: cargo test -p aether-integration-tests --bins --tests
 
       - name: Show sccache stats
         if: always()

apps/aether-gateway/src/ai_serving/api.rs

@@ -69,6 +69,9 @@ pub(crate) use aether_ai_formats::api::{
 };
 pub(crate) use aether_ai_formats::protocol::stream::CanonicalUsage as StreamingCanonicalUsage;
 pub(crate) use aether_ai_formats::CODEX_RESPONSES_LITE_HEADER;
+/// Codex client identity headers re-exported for out-of-crate probe binaries,
+/// which must reach `aether_ai_formats` through this seam.
+pub use aether_ai_formats::{CODEX_CLIENT_ORIGINATOR, CODEX_CLIENT_USER_AGENT};
 
 pub(crate) fn parse_direct_request_body(
     parts: &http::request::Parts,

apps/aether-gateway/src/ai_serving/mod.rs

@@ -52,16 +52,18 @@ pub(crate) use self::planner::{
     build_standard_family_sync_plan_and_reports, build_standard_stream_plan_from_decision,
     build_standard_sync_plan_from_decision, candidate_auth_channel_skip_reason,
     codex_model_capabilities_for_transport, extract_pool_sticky_session_token,
-    maybe_build_stream_decision_payload, maybe_build_stream_plan_payload,
-    maybe_build_sync_decision_payload, maybe_build_sync_plan_payload,
-    planner_is_matching_stream_request, provider_key_pool_score_id, provider_key_pool_score_scope,
-    read_candidate_transport_snapshot, record_local_runtime_candidate_skip_reason,
+    maybe_build_responses_websocket_decision, maybe_build_stream_decision_payload,
+    maybe_build_stream_plan_payload, maybe_build_sync_decision_payload,
+    maybe_build_sync_plan_payload, planner_is_matching_stream_request, provider_key_pool_score_id,
+    provider_key_pool_score_scope, read_candidate_transport_snapshot,
+    record_local_runtime_candidate_skip_reason, resolve_provider_chat_pii_redaction,
     resolve_tunnel_scheduler_affinity_context, resolve_upstream_is_stream_for_provider,
     set_local_openai_chat_execution_exhausted_diagnostic,
     set_local_openai_image_execution_exhausted_diagnostic, validate_final_openai_provider_request,
     CandidateFailureDiagnostic, CandidateFailureDiagnosticKind, EligibleLocalExecutionCandidate,
     GatewayAuthApiKeySnapshot, GatewayProviderTransportSnapshot, LocalExecutionAttemptSource,
     LocalExecutionCandidateKind, LocalResolvedOAuthRequestAuth, PlannerAppState,
+    ResponsesWebSocketBodyNormalization, ResponsesWebSocketDecision,
     SkippedLocalExecutionCandidate,
 };
 pub(crate) use self::pure::*;

apps/aether-gateway/src/ai_serving/planner/mod.rs

@@ -49,6 +49,7 @@ pub(crate) use self::plan_builders::{
 pub(crate) use self::pool_scores::{
     build_provider_key_pool_score_upsert, provider_key_pool_score_id, provider_key_pool_score_scope,
 };
+pub(crate) use self::redaction::resolve_provider_chat_pii_redaction;
 pub(crate) use self::request_gzip::resolve_transport_request_encoding_policy;
 pub(crate) use self::route::is_matching_stream_request as planner_is_matching_stream_request;
 pub(crate) use self::runtime_miss::{
@@ -80,8 +81,9 @@ pub(crate) use self::standard::{
     build_local_stream_plan_and_reports as build_standard_family_stream_plan_and_reports,
     build_local_sync_attempt_source as build_standard_family_sync_attempt_source,
     build_local_sync_plan_and_reports as build_standard_family_sync_plan_and_reports,
-    codex_model_capabilities_for_transport, set_local_openai_chat_execution_exhausted_diagnostic,
-    validate_final_openai_provider_request,
+    codex_model_capabilities_for_transport, maybe_build_responses_websocket_decision,
+    set_local_openai_chat_execution_exhausted_diagnostic, validate_final_openai_provider_request,
+    ResponsesWebSocketBodyNormalization, ResponsesWebSocketDecision,
 };
 pub(crate) use self::state::{
     GatewayAuthApiKeySnapshot, GatewayProviderTransportSnapshot, LocalResolvedOAuthRequestAuth,

apps/aether-gateway/src/ai_serving/planner/standard/mod.rs

@@ -42,13 +42,14 @@ pub(crate) use self::openai::{
     build_local_openai_responses_sync_attempt_source_for_kind,
     build_local_openai_responses_sync_plan_and_reports_for_kind, copy_request_number_field,
     copy_request_number_field_as, map_openai_reasoning_effort_to_claude_output,
-    map_openai_reasoning_effort_to_gemini_budget, maybe_build_stream_local_decision_payload,
+    map_openai_reasoning_effort_to_gemini_budget, maybe_build_responses_websocket_decision,
+    maybe_build_stream_local_decision_payload,
     maybe_build_stream_local_openai_responses_decision_payload,
     maybe_build_sync_local_decision_payload,
     maybe_build_sync_local_openai_embedding_decision_payload,
     maybe_build_sync_local_openai_responses_decision_payload, parse_openai_stop_sequences,
     resolve_openai_chat_max_tokens, set_local_openai_chat_execution_exhausted_diagnostic,
-    value_as_u64,
+    value_as_u64, ResponsesWebSocketBodyNormalization, ResponsesWebSocketDecision,
 };
 pub(crate) use crate::ai_serving::normalize_standard_request_to_openai_chat_request;
 pub(crate) use crate::ai_serving::{

apps/aether-gateway/src/ai_serving/planner/standard/openai/mod.rs

@@ -23,6 +23,8 @@ pub(crate) use responses::{
     build_local_openai_responses_stream_plan_and_reports_for_kind,
     build_local_openai_responses_sync_attempt_source_for_kind,
     build_local_openai_responses_sync_plan_and_reports_for_kind,
+    maybe_build_responses_websocket_decision,
     maybe_build_stream_local_openai_responses_decision_payload,
-    maybe_build_sync_local_openai_responses_decision_payload,
+    maybe_build_sync_local_openai_responses_decision_payload, ResponsesWebSocketBodyNormalization,
+    ResponsesWebSocketDecision,
 };