Fimeg/letta-server
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

fix: remove duplicate provider trace logging and dead code (#9278)

Browse Source 
Provider traces were being created twice per step:
1. Via `request_async_with_telemetry` / `log_provider_trace_async` in LLMClient
2. Via direct `create_provider_trace_async` calls in LettaAgent

This caused duplicate records in provider_trace_metadata (Postgres) and
llm_traces (ClickHouse) for every agent step.

Changes:
- Remove redundant direct `create_provider_trace_async` calls from letta_agent.py
- Remove no-op `stream_async_with_telemetry` method (was just a pass-through to `stream_async`)
- Update callers to use `stream_async` directly

🤖 Generated with [Letta Code](https://letta.com)

Co-authored-by: Letta <noreply@letta.com>
This commit is contained in:
Kian Jones
2026-02-04 11:40:12 -08:00
committed by Caren Thomas
parent cc3b0f13a6
commit 203b6ead7c
3 changed files with 2 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
letta/agents/letta_agent.py
View File

@@ -1490,7 +1490,7 @@ class LettaAgent(BaseAgent):
# Attempt LLM request with telemetry wrapper # Attempt LLM request with telemetry wrapper
return ( return (
request_data, request_data,
await llm_client.stream_async_with_telemetry(request_data, agent_state.llm_config), await llm_client.stream_async(request_data, agent_state.llm_config),
current_in_context_messages, current_in_context_messages,
new_in_context_messages, new_in_context_messages,
valid_tool_names, valid_tool_names,

8
letta/llm_api/llm_client_base.py
View File

@@ -127,14 +127,6 @@ class LLMClientBase:
except Exception as e: except Exception as e:
logger.warning(f"Failed to log telemetry: {e}") logger.warning(f"Failed to log telemetry: {e}")
async def stream_async_with_telemetry(self, request_data: dict, llm_config: LLMConfig):
"""Returns raw stream. Caller should log telemetry after processing via log_provider_trace_async().
Call set_telemetry_context() first to set agent_id, run_id, etc.
After consuming the stream, call log_provider_trace_async() with the response data.
"""
return await self.stream_async(request_data, llm_config)
async def log_provider_trace_async( async def log_provider_trace_async(
self, self,
request_data: dict, request_data: dict,

2
letta/services/summarizer/summarizer.py
View File

@@ -542,7 +542,7 @@ async def simple_summary(
) )
# AnthropicClient.stream_async sets request_data["stream"] = True internally. # AnthropicClient.stream_async sets request_data["stream"] = True internally.
stream = await llm_client.stream_async_with_telemetry(req_data, summarizer_llm_config) stream = await llm_client.stream_async(req_data, summarizer_llm_config)
async for _chunk in interface.process(stream): async for _chunk in interface.process(stream):
# We don't emit anything; we just want the fully-accumulated content. # We don't emit anything; we just want the fully-accumulated content.
pass pass