Skip to content

feat(langchain): Change LLM span operation to generate_text #5705

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
ericapisani wants to merge 3 commits into
base: master
Choose a base branch
from

ref(langchain): Remove agent name from on_llm_start and clean up tests

30e22ba
Select commit
Loading
Failed to load commit list.
Open

feat(langchain): Change LLM span operation to generate_text #5705

ref(langchain): Remove agent name from on_llm_start and clean up tests
30e22ba
Select commit
Loading
Failed to load commit list.
@sentry/warden / warden: code-review completed Mar 20, 2026 in 1m 6s

1 issue

code-review: Found 1 issue (1 medium)

Medium

GEN_AI_AGENT_NAME not captured in on_llm_start despite PR description - `sentry_sdk/integrations/langchain.py:381`

The PR description states that "when an LLM is invoked within an agent context, the agent name is now captured on the span via GEN_AI_AGENT_NAME", but the on_llm_start method does not call _get_current_agent() or set SPANDATA.GEN_AI_AGENT_NAME. The parallel method on_chat_model_start (lines 463-465) does capture the agent name correctly. This means LLM calls via on_llm_start will not have agent context attached, reducing observability as promised.

Duration: 1m 4s · Tokens: 248.5k in / 3.3k out · Cost: $0.67 (+extraction: $0.00, +fix_gate: $0.00)

Annotations

Check warning on line 381 in sentry_sdk/integrations/langchain.py

See this annotation in the file changed.

@sentry-warden sentry-warden / warden: code-review

GEN_AI_AGENT_NAME not captured in on_llm_start despite PR description 

The PR description states that "when an LLM is invoked within an agent context, the agent name is now captured on the span via GEN_AI_AGENT_NAME", but the `on_llm_start` method does not call `_get_current_agent()` or set `SPANDATA.GEN_AI_AGENT_NAME`. The parallel method `on_chat_model_start` (lines 463-465) does capture the agent name correctly. This means LLM calls via `on_llm_start` will not have agent context attached, reducing observability as promised.
View more details on @sentry/warden