admin/dify
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

revert: "fix(ops): add streaming metrics and LLM span for agent-chat traces" (#29469)

Browse Source
This commit is contained in:
-LAN-
2025-12-11 12:53:37 +08:00
committed by GitHub
parent 1847609926
commit 2e1efd62e1
6 changed files with 7 additions and 171 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
api/core/app/task_pipeline/easy_ui_based_generate_task_pipeline.py
View File

@@ -332,12 +332,6 @@ class EasyUIBasedGenerateTaskPipeline(BasedGenerateTaskPipeline):
if not self._task_state.llm_result.prompt_messages:
self._task_state.llm_result.prompt_messages = chunk.prompt_messages
# Track streaming response times
if self._task_state.first_token_time is None:
self._task_state.first_token_time = time.perf_counter()
self._task_state.is_streaming_response = True
self._task_state.last_token_time = time.perf_counter()
# handle output moderation chunk
should_direct_answer = self._handle_output_moderation_chunk(cast(str, delta_text))
if should_direct_answer:
@@ -404,18 +398,6 @@ class EasyUIBasedGenerateTaskPipeline(BasedGenerateTaskPipeline):
message.total_price = usage.total_price
message.currency = usage.currency
self._task_state.llm_result.usage.latency = message.provider_response_latency
# Add streaming metrics to usage if available
if self._task_state.is_streaming_response and self._task_state.first_token_time:
start_time = self.start_at
first_token_time = self._task_state.first_token_time
last_token_time = self._task_state.last_token_time or first_token_time
usage.time_to_first_token = round(first_token_time - start_time, 3)
usage.time_to_generate = round(last_token_time - first_token_time, 3)
# Update metadata with the complete usage info
self._task_state.metadata.usage = usage
message.message_metadata = self._task_state.metadata.model_dump_json()
if trace_manager: