From aa3e2ddc8f5c575125eb5ef0fe8c5a2ec86e7be1 Mon Sep 17 00:00:00 2001
From: zyycn <zyycn@users.noreply.github.com>
Date: Sat, 25 Jul 2026 03:26:09 +0800
Subject: [PATCH] fix(openai): align context and catalog tolerance

Co-authored-by: Codex <noreply@openai.com>
---
 .../providers/openai/src/transport/catalog.rs |  3 +
 .../providers/openai/src/transport/request.rs | 86 +++++++------------
 .../openai/tests/transport/catalog.rs         | 20 ++++-
 .../openai/tests/transport/request.rs         | 81 +++++++++++++++++
 4 files changed, 132 insertions(+), 58 deletions(-)

diff --git a/backend/crates/providers/openai/src/transport/catalog.rs b/backend/crates/providers/openai/src/transport/catalog.rs
index b8d5b0086..300f33b45 100644
--- a/backend/crates/providers/openai/src/transport/catalog.rs
+++ b/backend/crates/providers/openai/src/transport/catalog.rs
@@ -165,6 +165,9 @@ pub enum CodexCatalogVisibility {
     Hide,
     /// 不进入 picker。
     None,
+    /// 上游新增的可见性值；保留模型条目但不作本地可见性判断。
+    #[serde(other)]
+    Unknown,
 }
 
 /// 一个已完整校验的 Codex 真实模型。
diff --git a/backend/crates/providers/openai/src/transport/request.rs b/backend/crates/providers/openai/src/transport/request.rs
index c90a2f3a3..89090a208 100644
--- a/backend/crates/providers/openai/src/transport/request.rs
+++ b/backend/crates/providers/openai/src/transport/request.rs
@@ -1,6 +1,7 @@
 //! 核心 Generate operation 到 Codex Responses wire request 的严格编码。
 
 use gateway_core::operation::GenerateRequest;
+use gateway_protocol::openai::WS_REQUEST_HEADER_RESPONSES_LITE_CLIENT_METADATA_KEY;
 use serde_json::{Map, Value};
 use sha2::{Digest, Sha256};
 
@@ -127,64 +128,37 @@ struct ExtractedRequestContext {
 impl ExtractedRequestContext {
     fn from_body(body: &Map<String, Value>) -> Self {
         Self {
-            turn_state: body_or_metadata_string(
-                body,
-                &["turnState", "turn_state", "x-codex-turn-state"],
-            ),
-            turn_metadata: body_or_metadata_string(
-                body,
-                &["turnMetadata", "turn_metadata", "x-codex-turn-metadata"],
-            ),
-            beta_features: body_or_metadata_string(body, &["betaFeatures", "beta_features"]),
-            version: body_or_metadata_string(body, &["version"]),
-            include_timing_metrics: body_or_metadata_string(
-                body,
-                &["includeTimingMetrics", "include_timing_metrics"],
-            ),
-            codex_window_id: body_or_metadata_string(
-                body,
-                &["codexWindowId", "codex_window_id", "x-codex-window-id"],
-            ),
-            parent_thread_id: body_or_metadata_string(
-                body,
-                &[
-                    "parentThreadId",
-                    "parent_thread_id",
-                    "x-codex-parent-thread-id",
-                ],
-            ),
-            conversation_id: body_or_metadata_string(body, &["conversation_id", "conversationId"]),
-            session_id: body_or_metadata_string(body, &["session_id", "sessionId"]),
-            thread_id: body_or_metadata_string(body, &["thread_id", "threadId"]),
-            client_request_id: body_or_metadata_string(
-                body,
-                &[
-                    "x-client-request-id",
-                    "client_request_id",
-                    "clientRequestId",
-                ],
-            ),
-            turn_id: body_or_metadata_string(body, &["turn_id", "turnId", "x-codex-turn-id"]),
-            responses_lite: body_or_metadata_string(
-                body,
-                &["ws_request_header_x_openai_internal_codex_responses_lite"],
-            ),
-            memgen_request: body_or_metadata_string(
-                body,
-                &["x-openai-memgen-request", "memgen_request"],
-            ),
+            turn_state: body_string(body, "turnState"),
+            turn_metadata: body_string(body, "turnMetadata"),
+            beta_features: body_string(body, "betaFeatures"),
+            version: body_string(body, "version"),
+            include_timing_metrics: body_string(body, "includeTimingMetrics"),
+            codex_window_id: body_string(body, "codexWindowId"),
+            parent_thread_id: body_string(body, "parentThreadId"),
+            conversation_id: body_string(body, "conversation_id"),
+            session_id: body_string(body, "session_id"),
+            thread_id: body_string(body, "thread_id"),
+            client_request_id: body_string(body, "x-client-request-id"),
+            turn_id: body_string(body, "turn_id"),
+            // Responses Lite 在 WebSocket body 中的这个键是官方 header 投影，
+            // 不是普通上下文字段的 metadata 回退。
+            responses_lite: body
+                .get("client_metadata")
+                .and_then(Value::as_object)
+                .and_then(|metadata| {
+                    non_empty_string(
+                        metadata.get(WS_REQUEST_HEADER_RESPONSES_LITE_CLIENT_METADATA_KEY),
+                    )
+                }),
+            // Memory consolidation 只由官方请求头提供；body 中同名字段不参与
+            // transport 事实提取。
+            memgen_request: None,
         }
     }
 }
 
-fn body_or_metadata_string(body: &Map<String, Value>, keys: &[&str]) -> Option<String> {
-    keys.iter()
-        .find_map(|key| non_empty_string(body.get(*key)))
-        .or_else(|| {
-            let metadata = body.get("client_metadata")?.as_object()?;
-            keys.iter()
-                .find_map(|key| non_empty_string(metadata.get(*key)))
-        })
+fn body_string(body: &Map<String, Value>, key: &str) -> Option<String> {
+    non_empty_string(body.get(key))
 }
 
 fn non_empty_string(value: Option<&Value>) -> Option<String> {
@@ -528,10 +502,12 @@ fn apply_protocol_context(request: &mut CodexResponsesRequest, context: &Map<Str
         .parent_thread_id
         .take()
         .or_else(|| context_string(context, "parent_thread_id"));
+    let prompt_cache_key = request.prompt_cache_key().map(ToOwned::to_owned);
     request.client_conversation_id = request
         .client_conversation_id
         .take()
-        .or_else(|| context_string(context, "conversation_id"));
+        .or_else(|| context_string(context, "conversation_id"))
+        .or(prompt_cache_key);
     request.client_session_id = request
         .client_session_id
         .take()
diff --git a/backend/crates/providers/openai/tests/transport/catalog.rs b/backend/crates/providers/openai/tests/transport/catalog.rs
index 9232ca2d9..d6ec69358 100644
--- a/backend/crates/providers/openai/tests/transport/catalog.rs
+++ b/backend/crates/providers/openai/tests/transport/catalog.rs
@@ -1,9 +1,9 @@
 use chrono::{TimeZone, Utc};
 use provider_openai::transport::profile::{CodexWireProfile, CodexWireProfileState};
 use provider_openai::transport::{
-    CodexBackendClient, CodexCatalogCapabilityEvidence, CodexClientError, CodexModelCatalogError,
-    CodexRequestContext, MAX_CODEX_MODEL_CATALOG_BYTES, build_reqwest_client,
-    parse_codex_model_catalog,
+    CodexBackendClient, CodexCatalogCapabilityEvidence, CodexCatalogVisibility, CodexClientError,
+    CodexModelCatalogError, CodexRequestContext, MAX_CODEX_MODEL_CATALOG_BYTES,
+    build_reqwest_client, parse_codex_model_catalog,
 };
 use wiremock::matchers::{header, method, path, query_param};
 use wiremock::{Mock, MockServer, ResponseTemplate};
@@ -172,6 +172,20 @@ fn unknown_input_modality_should_degrade_capability_evidence_to_unknown() {
     );
 }
 
+#[test]
+fn unknown_visibility_should_degrade_without_rejecting_the_snapshot() {
+    let snapshot = parse_codex_model_catalog(
+        br#"{"models":[{"slug":"gpt-future","display_name":"Future","visibility":"preview_only"}]}"#,
+        None,
+    )
+    .expect("future visibility should not reject the snapshot");
+
+    assert_eq!(
+        snapshot.models()[0].metadata().visibility(),
+        Some(CodexCatalogVisibility::Unknown)
+    );
+}
+
 #[test]
 fn invalid_request_slug_should_fail_the_entire_snapshot() {
     let result = parse_codex_model_catalog(
diff --git a/backend/crates/providers/openai/tests/transport/request.rs b/backend/crates/providers/openai/tests/transport/request.rs
index ae64e441c..aafaa4fb8 100644
--- a/backend/crates/providers/openai/tests/transport/request.rs
+++ b/backend/crates/providers/openai/tests/transport/request.rs
@@ -126,6 +126,87 @@ fn encoder_should_forward_the_client_prompt_cache_key() {
     );
 }
 
+#[test]
+fn encoder_should_restore_conversation_fallback_after_body_and_context_values() {
+    let request = request(Map::from_iter([
+        ("model".to_owned(), json!("client-model")),
+        ("input".to_owned(), json!("prompt")),
+        ("prompt_cache_key".to_owned(), json!("cache-conversation")),
+    ]));
+
+    let encoded = encode_generate_request(&request, "gpt-test").expect("encode");
+
+    assert_eq!(
+        encoded.client_conversation_id.as_deref(),
+        Some("cache-conversation")
+    );
+}
+
+#[test]
+fn encoder_should_ignore_legacy_context_aliases_and_metadata_fallbacks() {
+    let request = request(Map::from_iter([
+        ("model".to_owned(), json!("client-model")),
+        ("input".to_owned(), json!("prompt")),
+        ("turn_state".to_owned(), json!("legacy-turn-state")),
+        (
+            "x-codex-turn-state".to_owned(),
+            json!("legacy-header-turn-state"),
+        ),
+        ("turn_metadata".to_owned(), json!("legacy-turn-metadata")),
+        ("beta_features".to_owned(), json!("legacy-beta")),
+        ("include_timing_metrics".to_owned(), json!("legacy-timing")),
+        ("codex_window_id".to_owned(), json!("legacy-window")),
+        (
+            "x-codex-window-id".to_owned(),
+            json!("legacy-header-window"),
+        ),
+        ("parent_thread_id".to_owned(), json!("legacy-parent")),
+        (
+            "x-codex-parent-thread-id".to_owned(),
+            json!("legacy-header-parent"),
+        ),
+        ("conversationId".to_owned(), json!("legacy-conversation")),
+        ("sessionId".to_owned(), json!("legacy-session")),
+        ("threadId".to_owned(), json!("legacy-thread")),
+        ("client_request_id".to_owned(), json!("legacy-request")),
+        ("clientRequestId".to_owned(), json!("legacy-camel-request")),
+        ("turnId".to_owned(), json!("legacy-turn")),
+        ("x-codex-turn-id".to_owned(), json!("legacy-header-turn")),
+        (
+            "client_metadata".to_owned(),
+            json!({
+                "turnState": "metadata-turn-state",
+                "turnMetadata": "metadata-turn-metadata",
+                "conversation_id": "metadata-conversation",
+                "session_id": "metadata-session",
+                "thread_id": "metadata-thread",
+                "x-codex-window-id": "metadata-window"
+            }),
+        ),
+    ]));
+
+    let encoded = encode_generate_request(&request, "gpt-test").expect("encode");
+
+    assert_eq!(
+        (
+            encoded.turn_state,
+            encoded.turn_metadata,
+            encoded.beta_features,
+            encoded.include_timing_metrics,
+            encoded.codex_window_id,
+            encoded.parent_thread_id,
+            encoded.client_conversation_id,
+            encoded.client_session_id,
+            encoded.client_thread_id,
+            encoded.client_request_id,
+            encoded.client_turn_id,
+        ),
+        (
+            None, None, None, None, None, None, None, None, None, None, None,
+        )
+    );
+}
+
 #[test]
 fn encoder_should_project_explicit_websocket_transport_without_touching_body() {
     let payload = ProtocolPayload::json_object(