Oleksandr Bezdieniezhnykh f5366bbca1 [AZ-698] Multi-flight tlog handling: segment first, pick last flight ...

Real derkachi.tlog covers 3 takeoffs at the same field but the
uploaded video covers only the last. Original NCC argmax + AZ-405
head-takeoff fallback both biased toward flight 1, violating the
spec's "the last chunk in tlog is relevant" framing.

Patch: pre-NCC flight segmenter partitions the IMU energy stream
into distinct flights (threshold + gap walk); find_aligned_window
restricts NCC search to the last segment; low-confidence fallback
uses that segment's start instead of head-takeoff detection.
AlignedWindow gains flight_count_detected + selected_flight_index
for FDR-visible audit.

7 new unit tests (segmenter shapes + end-to-end multi-flight
pipeline + segmented fallback path). 19 AZ-698 tests pass, 113
in the regression slice. Zero new mypy --strict errors.

Co-authored-by: Cursor <cursoragent@cursor.com>

2026-05-20 16:44:41 +03:00

..

backlog

[AZ-589] [AZ-590] [AZ-591] [AZ-592] [AZ-593] Re-classify cycle1 gate findings

2026-05-16 12:45:58 +03:00

done

[AZ-698] Multi-flight tlog handling: segment first, pick last flight

2026-05-20 16:44:41 +03:00

todo

[AZ-698] Tlog trim + mid-flight alignment for replay

2026-05-20 16:29:59 +03:00

_dependencies_table.md

[AZ-696] chore: cycle-2 bootstrap — gitignore tlog inputs, Step 9 PBIs

2026-05-20 15:50:50 +03:00