Skip to content

fix(langchain): detach existing SpanHolder token before overwrite in _create_llm_span #3958

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

Merged
OzBenSimhonTraceloop merged 4 commits into from
Apr 15, 2026
Merged

fix(langchain): detach existing SpanHolder token before overwrite in _create_llm_span #3958

Changes from 2 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
c056d6f
fix(langchain): detach existing SpanHolder token before overwrite in …
saivedant169 Apr 9, 2026
39bc0d9
fix: detach old token before creating suppression to preserve context…
saivedant169 Apr 12, 2026
abadc39
fix: detach duplicate run_id token before _create_span overwrites holder
saivedant169 Apr 14, 2026
6f38e1f
Merge branch 'main' into fix/langchain-span-holder-overwrite
OzBenSimhonTraceloop Apr 15, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 8 additions & 0 deletions ...try-instrumentation-langchain/opentelemetry/instrumentation/langchain/callback_handler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -462,6 +462,14 @@ def _create_llm_span(
span, GenAIAttributes.GEN_AI_OPERATION_NAME, operation_name
)

# Detach any existing holder's token before creating the suppression
# token. The ordering matters: if we detach after attaching the
# suppression, ContextVar.reset() restores context to before the span,
# wiping the suppression flag and causing duplicate downstream spans.
existing_holder = self.spans.get(run_id)
if existing_holder is not None and existing_holder.token is not None:
self._safe_detach_context(existing_holder.token)

# we already have an LLM span by this point,
# so skip any downstream instrumentation from here
try:
Expand Down
Loading