[Bugfix][HunyuanImage] fix accuracy in stream mode (#4265)

Signed-off-by: dengyunyang <584797741@qq.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>

vllm_omni/engine/output_processor.py

@@ -269,6 +269,10 @@ class OmniRequestState(RequestState):
         # tokens, so we always store a cumulative copy here.
         base_output.cumulative_token_ids = list(self.detokenizer.output_token_ids)
 
+        # Attach cumulative_text only at the final step for inter-stage use.
+        if finish_reason is not None and hasattr(self.detokenizer, "output_text"):
+            base_output.cumulative_text = self.detokenizer.output_text
+
         if not hasattr(base_output, "multimodal_output"):
             setattr(base_output, "multimodal_output", {})
         if self.mm_accumulated:

vllm_omni/model_executor/stage_input_processors/hunyuan_image3.py

@@ -185,7 +185,8 @@ def ar2diffusion(
     for i, ar_output in enumerate(ar_outputs):
         output = ar_output.outputs[0]
         generated_token_ids = output.cumulative_token_ids
-        generated_text = getattr(output, "text", "") or ""
+        # Prefer cumulative_text, fallback to text if aggregation dropped it
+        generated_text = getattr(output, "cumulative_text", None) or getattr(output, "text", "") or ""
 
         # Get original prompt info
         original_prompt = prompt[i] if i < len(prompt) else {}