youngkingdom/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-04-21 19:27:40 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix: Drain non-stream plugin chunk iterator (#31564)

Browse Source
This commit is contained in:
盐粒 Yanli
2026-01-30 16:54:56 +08:00
committed by GitHub
parent 89abea26f9
commit 5a7dfd15b8
2 changed files with 44 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
api/core/model_runtime/model_providers/__base/large_language_model.py
View File

@ -92,6 +92,10 @@ def _build_llm_result_from_first_chunk(
Build a single `LLMResult` from the first returned chunk.
This is used for `stream=False` because the plugin side may still implement the response via a chunked stream.
Note:
This function always drains the `chunks` iterator after reading the first chunk to ensure any underlying
streaming resources are released (e.g., HTTP connections owned by the plugin runtime).
"""
content = ""
content_list: list[PromptMessageContentUnionTypes] = []
@ -99,18 +103,25 @@ def _build_llm_result_from_first_chunk(
system_fingerprint: str | None = None
tools_calls: list[AssistantPromptMessage.ToolCall] = []
first_chunk = next(chunks, None)
if first_chunk is not None:
if isinstance(first_chunk.delta.message.content, str):
content += first_chunk.delta.message.content
elif isinstance(first_chunk.delta.message.content, list):
content_list.extend(first_chunk.delta.message.content)
try:
first_chunk = next(chunks, None)
if first_chunk is not None:
if isinstance(first_chunk.delta.message.content, str):
content += first_chunk.delta.message.content
elif isinstance(first_chunk.delta.message.content, list):
content_list.extend(first_chunk.delta.message.content)
if first_chunk.delta.message.tool_calls:
_increase_tool_call(first_chunk.delta.message.tool_calls, tools_calls)
if first_chunk.delta.message.tool_calls:
_increase_tool_call(first_chunk.delta.message.tool_calls, tools_calls)
usage = first_chunk.delta.usage or LLMUsage.empty_usage()
system_fingerprint = first_chunk.system_fingerprint
usage = first_chunk.delta.usage or LLMUsage.empty_usage()
system_fingerprint = first_chunk.system_fingerprint
finally:
try:
for _ in chunks:
pass
except Exception:
logger.debug("Failed to drain non-stream plugin chunk iterator.", exc_info=True)
return LLMResult(
model=model,