From 4f010cd4f5bf98c3a7683191b8b0294b91c6c14e Mon Sep 17 00:00:00 2001
From: Yansong Zhang <916125788@qq.com>
Date: Thu, 9 Apr 2026 12:31:49 +0800
Subject: [PATCH] fix(api): stop emitting StreamChunkEvent from tool path to
 prevent answer duplication

The EventAdapter was converting every LLMResultChunk from the agent
strategy into StreamChunkEvent. Combined with the answer node's
{{#agent.text#}} variable output, this caused the final answer to
appear twice (e.g., "It is 2026-04-09 04:27:45.It is 2026-04-09 04:27:45.").

Now LLMResultChunk from strategy output is silently consumed (text still
accumulates in AgentResult.text via the strategy). Only AgentLogEvent
(thought/tool_call/round) is forwarded to the pipeline.

Known remaining issues:
- workflow/message level total_tokens=0 (node level is correct at 33)
  because pipeline aggregation doesn't include agent-v2 node tokens
- Turn 2 SSE delivery timing with Redis pubsub (celery executes OK)

Made-with: Cursor
---
 api/core/workflow/nodes/agent_v2/event_adapter.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/api/core/workflow/nodes/agent_v2/event_adapter.py b/api/core/workflow/nodes/agent_v2/event_adapter.py
index e08bb43a87..6e11a04948 100644
--- a/api/core/workflow/nodes/agent_v2/event_adapter.py
+++ b/api/core/workflow/nodes/agent_v2/event_adapter.py
@@ -39,7 +39,7 @@ class AgentV2EventAdapter:
                 if isinstance(item, AgentLog):
                     yield self._convert_agent_log(item, node_id=node_id, node_execution_id=node_execution_id)
                 elif isinstance(item, LLMResultChunk):
-                    yield from self._convert_llm_chunk(item, node_id=node_id)
+                    pass
         except StopIteration as e:
             result: AgentResult = e.value
             return result