Repository navigation
fix(ui): do not count no-data guidance as failed chat steps - #353
Merged
Merged
Conversation
Since empty results became no_data and unknown_service guidance, chat counted them as failed steps, so a successful investigation showed "2 steps failed" while the agent was only told which signal exists. Guidance results are no longer listed as failures; other tool errors still are. Claude-Session: https://claude.ai/code/session_018HfyEXHyGD1utmKF4CQtyQ
vishr
force-pushed
the
fix/chat-guidance-not-failures
branch
from
October 18, 2026 23:06
7f9bf6f to
d4677a8
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
no_dataandunknown_serviceguidance (fix(mcp): answer empty results with guidance and keep empty panels out of dashboards #347), chat counted them as failed steps. A successful investigation showed "2 steps failed" although the agent was only told which signal exists, and the landing recordings kept failing their no-failed-step check.The agent's own rejected drafts (for example a
query_telemetrypanel it then corrects) still count as failed steps. Hiding those reliably needs a distinct server error code for validation rejections; a name- or target-matching heuristic hid real failures in review and was dropped.Verification
just ui,just ui-check.just checkin the pre-push hook.