Mahdi Bazrafshan d5ccec2f2c feat(config): apply fixed_size ±3 as stabilized defaults ...

Why:
- Final benchmark selected fixed_size with neighbor expansion ±3 as the winning Candidate.

Changes:
- Set neighbor_prev/neighbor_next defaults to 3 in Settings.
- Default Query tab to fixed_size ±3/3 and Benchmarks to single-strategy fixed_size.

Impact:
- API and Dashboard runs use ±3 unless explicitly overridden.

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

2026-08-22 13:27:15 +03:30

..

admin

feat(admin): add embedding model role and threshold APIs

2026-08-10 14:13:07 +03:30

benchmarking

feat(dashboard): add decision board for strategy selection

2026-08-17 14:22:21 +03:30

chunking

fix(chunking): require semantic boundary detection

2026-08-10 14:12:45 +03:30

core

feat(config): apply fixed_size ±3 as stabilized defaults

2026-08-22 13:27:15 +03:30

documents

feat(documents): snapshot boundary and corpus models on process

2026-08-10 14:13:07 +03:30

static

feat(config): apply fixed_size ±3 as stabilized defaults

2026-08-22 13:27:15 +03:30

storage

feat(dashboard): add decision board for strategy selection

2026-08-17 14:22:21 +03:30

main.py

feat(admin): add admin backend endpoints and service layer

2026-07-29 17:53:43 +03:30