fix: correct category labels, detector evaluation and IMM timing - #161
Conversation
|
Warning Review limit reachedNext included review available in 21 minutes. View limit detailsLimit details: You’ve used the included review currently available. You've used all free OSS reviews for now. Wait for the free limit to reset to keep reviewing this public repository. Review configuration: ⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Advanced Run ID: ⛔ Files ignored due to path filters (1)
📒 Files selected for processing (53)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Codecov Report❌ Patch coverage is
📢 Thoughts on this report? Let us know! |
|



Summary
Verification
Local broad-suite limitations
The feature-enabled workspace run excludes thresh-py. Its existing debug throughput gate failed at 3.8 Hz; unchanged baseline also fails locally at 5.2 Hz, below the unchanged 10 Hz threshold. Rerunning the remaining tests reached an existing cache-directory test denied by the sandbox for a home-directory write. Neither test nor threshold was weakened. Focused changes pass; full standard CI and optional-runtime checks remain authoritative merge gates.
Scope boundaries
No live OpenSky data fetched/stored, no trained checkpoint release, no crates.io publication. Representative trained-model acceptance remains open. Short CLI tests are smoke only; default synthetic duration stays 30 seconds. Targets develop and depends on cleanup PR #159, which should merge first.