feat: support Responses to Chat (#5787)

* fix(openai): harden Chat-to-Responses compatibility

Add a shared Responses-to-Chat stream state machine and use it from the OpenAI relay path. Preserve assistant text alongside tool calls, bind tool argument deltas by output_index, map incomplete finish reasons, support reasoning/custom tool events, and buffer upstream SSE for non-stream Chat clients.

Add deterministic service tests and relay SSE tests for the conversion path.

Related to #5745.

* refactor: rename openaicompat to relayconvert for improved clarity

* feat(gemini): support responses request conversion

* feat: add responses to chat conversion support

* fix: harden responses chat conversion edge cases

web/default/src/features/channels/lib/advanced-custom.ts

@@ -43,6 +43,10 @@ export const ADVANCED_CUSTOM_CONVERTER_OPTIONS: Array<{
     value: 'openai_chat_completions_to_openai_responses',
     label: 'OpenAI Chat to OpenAI Responses',
   },
+  {
+    value: 'openai_responses_to_openai_chat_completions',
+    label: 'OpenAI Responses to OpenAI Chat',
+  },
   {
     value: 'gemini_generate_content_to_openai_chat_completions',
     label: 'Gemini Generate Content to OpenAI Chat',
@@ -326,6 +330,9 @@ export function getAdvancedCustomUpstreamPathPlaceholder(
   if (converter === 'openai_chat_completions_to_anthropic_messages') {
     return '/v1/messages'
   }
+  if (converter === 'openai_responses_to_openai_chat_completions') {
+    return '/v1/chat/completions'
+  }
   return '/v1/chat/completions'
 }
 
@@ -573,6 +580,9 @@ function isConverterPathAllowed(
   ) {
     return incomingPath === '/v1/chat/completions'
   }
+  if (converter === 'openai_responses_to_openai_chat_completions') {
+    return incomingPath === '/v1/responses'
+  }
   return (
     incomingPath.includes(':generateContent') ||
     incomingPath.includes(':streamGenerateContent')

web/default/src/features/channels/types.ts

@@ -131,6 +131,7 @@ export type AdvancedCustomConverter =
   | 'anthropic_messages_to_openai_chat_completions'
   | 'openai_chat_completions_to_anthropic_messages'
   | 'openai_chat_completions_to_openai_responses'
+  | 'openai_responses_to_openai_chat_completions'
   | 'gemini_generate_content_to_openai_chat_completions'
   | 'openai_chat_completions_to_gemini_generate_content'