修复 AI 网关流式断流:错误透传、自动降级,max_tokens 可缺省

internal/service/chatresponses.go

@@ -358,3 +358,32 @@ func (b *ChatRespBridge) Finish() []aiwire.ChatChunk {
 
 // Usage 返回聚合到的用量(供调用日志),上游未报告时为 nil。
 func (b *ChatRespBridge) Usage() *aiwire.Usage { return b.usage }
+
+// ChatResponseChunks 把完整 Chat 响应展开为 chunk 序列(内容与工具调用 →
+// 终块 → 可选 usage 块),供流式上游断流后的非流式降级结果推送。
+func ChatResponseChunks(resp *aiwire.ChatResponse, includeUsage bool) []aiwire.ChatChunk {
+	if len(resp.Choices) == 0 {
+		return nil
+	}
+	choice := resp.Choices[0]
+	mk := func(delta aiwire.Delta, finish *string) aiwire.ChatChunk {
+		return aiwire.ChatChunk{ID: resp.ID, Object: "chat.completion.chunk", Created: resp.Created,
+			Model: resp.Model, Choices: []aiwire.ChunkChoice{{Index: 0, Delta: delta, FinishReason: finish}}}
+	}
+	delta := aiwire.Delta{Role: "assistant", Content: choice.Message.Content.Text}
+	for i, tc := range choice.Message.ToolCalls {
+		delta.ToolCalls = append(delta.ToolCalls, aiwire.ToolCallDelta{Index: i, ID: tc.ID,
+			Type: "function", Function: aiwire.FunctionCallDelta{Name: tc.Function.Name, Arguments: tc.Function.Arguments}})
+	}
+	finish := choice.FinishReason
+	chunks := []aiwire.ChatChunk{mk(delta, nil), mk(aiwire.Delta{}, &finish)}
+	if includeUsage {
+		usage := resp.Usage
+		if usage == nil {
+			usage = &aiwire.Usage{}
+		}
+		chunks = append(chunks, aiwire.ChatChunk{ID: resp.ID, Object: "chat.completion.chunk",
+			Created: resp.Created, Model: resp.Model, Choices: []aiwire.ChunkChoice{}, Usage: usage})
+	}
+	return chunks
+}