shira-hermes

Archived

This repository has been archived on 2026-07-19. You can view files and clone it. You cannot open issues or pull requests or push a commit.

T

chaim 1739fa1211 fix(kb/chunker): drop false section matches from PDF tables of contents

ספר הליקויים produced 698 chunks, most of them junk. A line like
"3 . . . . . . . . . . . . . . . . . . . . . . . . . . הוראות החוק" from
its table of contents was being treated as section 3. Phone numbers like
"02-6709701" became section 02. Both of these polluted the index and
broke the browse view's readability.

Tighten _RE_SECTION so it requires either the explicit prefix (סעיף /
תקנה / §) OR real text immediately after the terminator — a row of dots
or more digits disqualifies. The scraped חוק הביטוח הלאומי still chunks
correctly because the scraper emits "סעיף N. ..." with the prefix.

Refs Task Master #2

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

2026-04-24 09:45:09 +00:00

.gitea/workflows

ci: add Gitea Actions CI/CD workflow

2026-04-14 04:15:48 +00:00

.taskmaster/tasks

feat(kb): Phase 1 — Israeli National Insurance knowledge base

2026-04-21 14:36:09 +00:00

api

fix(kb/chunker): drop false section matches from PDF tables of contents

2026-04-24 09:45:09 +00:00

config

feat: add skills, memory, delegation and self-learning (Phase 3)