feat: add internal tracing to components that use chat generators - #12075
Merged
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
github-actions
Bot
added
topic:tests
type:documentation
Contributor
Coverage report
Click to see where and how coverage changed
This report was generated by python-coverage-comment-action |
||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
sjrl
commented
Jul 21, 2026
Comment on lines
+385
to
+389
| # Capture the current span here so worker threads nest their generator spans under the component span. | ||
| parent_span = tracing.tracer.current_span() | ||
|
|
||
| with ThreadPoolExecutor(max_workers=self.max_workers) as executor: | ||
| results = executor.map(self._run_on_thread, image_contents) | ||
| results = executor.map(partial(self._run_on_thread, parent_span=parent_span), image_contents) |
Contributor
Author
There was a problem hiding this comment.
Note we only directly pass down a parent_span in the cases where the chat generator is being run in a separate thread or in an async context.
davidsbatista
approved these changes
Jul 21, 2026
davidsbatista
left a comment
davidsbatista
left a comment
Contributor
There was a problem hiding this comment.
Just a small suggestion. Looks good 👍🏽
…pset-ai/haystack into add-usage-tracking-internal-chat-gen
sjrl
enabled auto-merge (squash)
July 21, 2026 08:59
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Related Issues
Proposed Changes:
LLMEvaluator,LLMRanker,QueryExpander,LLMMetadataExtractor,LLMDocumentContentExtractorandLLMMessagesRouternow wrap their internalChatGeneratorcalls in ahaystack.chat_generator.runtracing span. These components do not returnChatMessageobjects, so the LLM token usage carried inreply.meta["usage"]was previously lost to tracers. The new span exposes the generator's replies via thehaystack.component.outputtag, so token usage is now visible in traces (requires content tracing to be enabled). When the generator runs across threads, the span is nested under the component's span.How did you test it?
New tests
Notes for the reviewer
Checklist
fix:,feat:,build:,chore:,ci:,docs:,style:,refactor:,perf:,test:and added!in case the PR includes breaking changes.