Merge pull request #3337 from ddnio/codex/openai-json-mode-developer-input

fix(openai): preserve JSON instructions in Codex OAuth input

backend/internal/service/openai_codex_transform.go

@@ -212,7 +212,9 @@ func applyCodexOAuthTransformWithOptions(reqBody map[string]any, opts codexOAuth
 		}
 	}
 
-	// 提取 input 中 role:"system" 消息至 instructions（OAuth 上游不支持 system role）。
+	// ChatGPT internal Codex endpoint does not accept role:"system".
+	// Keep the guidance in input as developer for Responses JSON mode, and
+	// also mirror it into instructions because Codex OAuth requires it.
 	if extractSystemMessagesFromInput(reqBody) {
 		result.Modified = true
 	}
@@ -948,10 +950,10 @@ func extractTextFromContent(content any) string {
 	}
 }
 
-// extractSystemMessagesFromInput scans the input array for items with role=="system",
-// removes them, and merges their content into reqBody["instructions"].
-// If instructions is already non-empty, extracted content is prepended with "\n\n".
-// Returns true if any system messages were extracted.
+// extractSystemMessagesFromInput scans input for role=="system", maps those
+// items to developer, and mirrors their text into reqBody["instructions"].
+// It preserves the input items so Responses JSON mode can still see JSON
+// instructions in input messages.
 func extractSystemMessagesFromInput(reqBody map[string]any) bool {
 	input, ok := reqBody["input"].([]any)
 	if !ok || len(input) == 0 {
@@ -959,25 +961,24 @@ func extractSystemMessagesFromInput(reqBody map[string]any) bool {
 	}
 
 	var systemTexts []string
-	remaining := make([]any, 0, len(input))
-
+	modified := false
 	for _, item := range input {
 		m, ok := item.(map[string]any)
 		if !ok {
-			remaining = append(remaining, item)
 			continue
 		}
 		if role, _ := m["role"].(string); role != "system" {
-			remaining = append(remaining, item)
 			continue
 		}
+		m["role"] = "developer"
+		modified = true
 		if text := extractTextFromContent(m["content"]); text != "" {
 			systemTexts = append(systemTexts, text)
 		}
 	}
 
 	if len(systemTexts) == 0 {
-		return false
+		return modified
 	}
 
 	extracted := strings.Join(systemTexts, "\n\n")
@@ -986,7 +987,6 @@ func extractSystemMessagesFromInput(reqBody map[string]any) bool {
 	} else {
 		reqBody["instructions"] = extracted
 	}
-	reqBody["input"] = remaining
 	return true
 }
 

backend/internal/service/openai_codex_transform_test.go

@@ -1094,10 +1094,14 @@ func TestExtractSystemMessagesFromInput(t *testing.T) {
 		require.True(t, result)
 		input, ok := reqBody["input"].([]any)
 		require.True(t, ok)
-		require.Len(t, input, 1)
+		require.Len(t, input, 2)
 		msg, ok := input[0].(map[string]any)
 		require.True(t, ok)
-		require.Equal(t, "user", msg["role"])
+		require.Equal(t, "developer", msg["role"])
+		require.Equal(t, "You are an assistant.", msg["content"])
+		user, ok := input[1].(map[string]any)
+		require.True(t, ok)
+		require.Equal(t, "user", user["role"])
 		require.Equal(t, "You are an assistant.", reqBody["instructions"])
 	})
 
@@ -1117,7 +1121,14 @@ func TestExtractSystemMessagesFromInput(t *testing.T) {
 		require.Equal(t, "Be helpful.", reqBody["instructions"])
 		input, ok := reqBody["input"].([]any)
 		require.True(t, ok)
-		require.Len(t, input, 0)
+		require.Len(t, input, 1)
+		msg, ok := input[0].(map[string]any)
+		require.True(t, ok)
+		require.Equal(t, "developer", msg["role"])
+		require.Equal(t, []any{
+			map[string]any{"type": "text", "text": "Be helpful."},
+		}, msg["content"])
+		require.Equal(t, "Be helpful.", reqBody["instructions"])
 	})
 
 	t.Run("multiple system messages concatenated", func(t *testing.T) {
@@ -1133,7 +1144,17 @@ func TestExtractSystemMessagesFromInput(t *testing.T) {
 		require.Equal(t, "First.\n\nSecond.", reqBody["instructions"])
 		input, ok := reqBody["input"].([]any)
 		require.True(t, ok)
-		require.Len(t, input, 1)
+		require.Len(t, input, 3)
+		first, ok := input[0].(map[string]any)
+		require.True(t, ok)
+		require.Equal(t, "developer", first["role"])
+		second, ok := input[1].(map[string]any)
+		require.True(t, ok)
+		require.Equal(t, "developer", second["role"])
+		user, ok := input[2].(map[string]any)
+		require.True(t, ok)
+		require.Equal(t, "user", user["role"])
+		require.Equal(t, "First.\n\nSecond.", reqBody["instructions"])
 	})
 
 	t.Run("mixed system and non-system preserves non-system", func(t *testing.T) {
@@ -1148,13 +1169,17 @@ func TestExtractSystemMessagesFromInput(t *testing.T) {
 		require.True(t, result)
 		input, ok := reqBody["input"].([]any)
 		require.True(t, ok)
-		require.Len(t, input, 2)
+		require.Len(t, input, 3)
 		first, ok := input[0].(map[string]any)
 		require.True(t, ok)
 		require.Equal(t, "user", first["role"])
 		second, ok := input[1].(map[string]any)
 		require.True(t, ok)
-		require.Equal(t, "assistant", second["role"])
+		require.Equal(t, "developer", second["role"])
+		third, ok := input[2].(map[string]any)
+		require.True(t, ok)
+		require.Equal(t, "assistant", third["role"])
+		require.Equal(t, "Sys prompt.", reqBody["instructions"])
 	})
 
 	t.Run("existing instructions prepended", func(t *testing.T) {
@@ -1168,6 +1193,11 @@ func TestExtractSystemMessagesFromInput(t *testing.T) {
 		result := extractSystemMessagesFromInput(reqBody)
 		require.True(t, result)
 		require.Equal(t, "Extracted.\n\nExisting instructions.", reqBody["instructions"])
+		input, ok := reqBody["input"].([]any)
+		require.True(t, ok)
+		msg, ok := input[0].(map[string]any)
+		require.True(t, ok)
+		require.Equal(t, "developer", msg["role"])
 	})
 }
 
@@ -1227,14 +1257,53 @@ func TestApplyCodexOAuthTransform_ExtractsSystemMessages(t *testing.T) {
 
 	input, ok := reqBody["input"].([]any)
 	require.True(t, ok)
-	require.Len(t, input, 1)
-	msg, ok := input[0].(map[string]any)
+	require.Len(t, input, 2)
+	system, ok := input[0].(map[string]any)
 	require.True(t, ok)
-	require.Equal(t, "user", msg["role"])
+	require.Equal(t, "developer", system["role"])
+	require.Equal(t, "You are a coding assistant.", system["content"])
+	user, ok := input[1].(map[string]any)
+	require.True(t, ok)
+	require.Equal(t, "user", user["role"])
+	require.Equal(t, "You are a coding assistant.", reqBody["instructions"])
+}
 
+func TestApplyCodexOAuthTransform_JsonObjectKeepsJsonInstructionInInput(t *testing.T) {
+	reqBody := map[string]any{
+		"model": "gpt-5.4",
+		"input": []any{
+			map[string]any{
+				"role":    "system",
+				"content": "You are an assistant. Output JSON only.",
+			},
+			map[string]any{
+				"role":    "user",
+				"content": "symbol data without the keyword",
+			},
+		},
+		"text": map[string]any{
+			"format": map[string]any{
+				"type": "json_object",
+			},
+		},
+	}
+
+	result := applyCodexOAuthTransform(reqBody, false, false)
+
+	require.True(t, result.Modified)
 	instructions, ok := reqBody["instructions"].(string)
 	require.True(t, ok)
-	require.Equal(t, "You are a coding assistant.", instructions)
+	require.Contains(t, instructions, "JSON")
+	input, ok := reqBody["input"].([]any)
+	require.True(t, ok)
+	require.Len(t, input, 2)
+	developer, ok := input[0].(map[string]any)
+	require.True(t, ok)
+	require.Equal(t, "developer", developer["role"])
+	require.Contains(t, developer["content"], "JSON")
+	user, ok := input[1].(map[string]any)
+	require.True(t, ok)
+	require.Equal(t, "user", user["role"])
 }
 
 func TestIsInstructionsEmpty(t *testing.T) {