user2595/codex-py
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(F-16): chunk quality gate + section classification

Browse Source 
3-signal quality filter (length/alpha-ratio/bib-score) + rule-based section classifier + retroactive CLI pass. 35 new tests, 287 total green.
This commit is contained in:
user2595
2026-06-15 01:22:44 +00:00
parent 1a9afb4433
commit 9647897173
9 changed files with 529 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
.env.example
View File

@@ -27,3 +27,8 @@ OPENALEX_MAILTO=you@example.com
# Nougat HTTP-Server (Jetson: http://192.168.178.103:8080 | lokal: http://localhost:8080)
# Used by `codex ingest <id> --rich` for full-PDF Mathpix Markdown output.
NOUGAT_URL=http://localhost:8080
# F-16 Chunk Quality Gate thresholds (all optional — defaults shown)
CHUNK_MIN_CHARS=60 # Discard chunks shorter than this many characters
CHUNK_MIN_ALPHA_RATIO=0.40 # Discard chunks with < 40% alphabetic characters
CHUNK_MAX_BIB_SCORE=0.70 # Discard chunks scoring above this bibliography threshold