perf(tracing): add llm.turn_call span to main-turn LLM call#3623
Merged
perf(tracing): add llm.turn_call span to main-turn LLM call#3623
Conversation
Rename existing llm_call spans in native.rs to llm.turn_call and add a provider field. The new name avoids collision with llm.chat_stream spans emitted at the provider layer (compatible.rs, ollama.rs). Both the production path (call_chat_with_tools) and the test path (call_llm_with_timeout) are updated. Closes #3619
2d88be4 to
3393afa
Compare
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
llm_calltracing span tollm.turn_callinnative.rs(both production and test paths)providerfield to the span so traces identify the active LLM backendllm.chat_streamspans at the provider layer (compatible.rs,ollama.rs)book/src/advanced/observability.mdspan reference tableMotivation
The main-turn LLM call was a silent gap in local Chrome traces — ~15 s of unattributed latency inside
agent.turn. This change makes the span visible asllm.turn_callwithmodelandproviderattributes, enabling bottleneck detection in Perfetto / chrome://tracing.Test plan
zeph-coretests passcargo +nightly fmt --check— cleancargo clippy --workspace --all-targets --features "desktop,ide,server,chat,pdf,scheduler" -- -D warnings— 0 warnings&'static strfield added)Closes #3619