Merged
Conversation
Wenyueh
requested review from
TianyiPeng and
Copilot
and removed request for
TianyiPeng
There was a problem hiding this comment.
Pull request overview
Adds selection-level wall-clock timing and total selection cost reporting to model selection results, so users can see end-to-end overhead in addition to per-model accuracy/latency/price.
Changes:
- Extend
SelectionResultswithselection_wall_time_secondsandselection_cost. - Print selection overhead in the
SelectionResults.__str__()summary output. - Measure wall time and compute aggregate (non-cached) cost in
BaseModelSelector.select_best().
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Track wall-clock time and actual API cost of the model selection process on SelectionResults
Cached (reused) responses are excluded from cost calculation — only fresh API calls count
Wall-clock time naturally reflects savings from parallel execution
Both metrics are displayed in the summary table output
Test plan
All 45 existing tests pass
Run a selection with warm cache and verify selection_cost drops to ~$0 while per-combo prices remain unchanged
Run with parallel=True and confirm selection_wall_time_seconds reflects actual elapsed time (not sum of sequential times)