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/i18n/locales/zh.json

@@ -2995,6 +2995,7 @@
     "OpenAI Rerank": "OpenAI 重排序",
     "OpenAI Responses": "OpenAI 响应",
     "OpenAI Responses Compact": "OpenAI 响应压缩",
+    "OpenAI Responses to OpenAI Chat": "OpenAI Responses 到 OpenAI Chat",
     "OpenAI, Anthropic, etc.": "OpenAI、Anthropic 等",
     "OpenAI, Anthropic, Google, etc.": "OpenAI、Anthropic、Google 等",
     "OpenAIMax": "OpenAIMax",
@@ -3675,8 +3676,8 @@
     "Resetting...": "重置中...",
     "Resolve Conflicts": "解决冲突",
     "Resource Configuration": "资源配置",
-    "Responding...": "正在回复...",
     "Resources": "资源",
+    "Responding...": "正在回复...",
     "Response": "响应",
     "Response Time": "响应时间",
     "Response time: {{duration}}": "响应时间：{{duration}}",