Chaim 8153bc9f03 fix(extractor): add regex fix for Hebrew law year gershayim corruption ...

תש[א-ת]+יי[א-ת] → תש[א-ת]+"[א-ת]  (e.g. תשכייה → תשכ"ה)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-05-25 16:12:20 +00:00

..

__init__.py

Initial commit: MCP server + web upload interface

2026-03-23 12:33:07 +00:00

analysis_docx_exporter.py

Pre-existing agent updates + analysis DOCX export

2026-04-16 18:49:10 +00:00

appraiser_facts_extractor.py

LLM session: async, 30min timeout, semantic chunking + parallel

2026-04-30 14:21:35 +00:00

audit.py

Add full decision writing pipeline: classify, extract, brainstorm, write, QA, export

2026-04-03 10:21:47 +00:00

block_writer.py

fix: prevent write_interim_draft context overflow (465K → ≤300K chars)

2026-05-10 10:49:47 +00:00

brainstorm.py

LLM session: async, 30min timeout, semantic chunking + parallel

2026-04-30 14:21:35 +00:00

chunker.py

feat(retrieval): track page_number on text chunks for multimodal hybrid boost

2026-05-03 19:49:41 +00:00

claims_extractor.py

LLM session: async, 30min timeout, semantic chunking + parallel

2026-04-30 14:21:35 +00:00

claude_session.py

fix: prevent write_interim_draft context overflow (465K → ≤300K chars)

2026-05-10 10:49:47 +00:00

db.py

feat(precedent-library): add district and chair_name to edit form

2026-05-19 12:16:43 +00:00

docx_exporter.py

feat(interim): include block-he opening in pre-ruling interim drafts

2026-05-04 17:25:54 +00:00

docx_retrofit.py

Retrofit: tighten yod-bet pattern, add cover-block fallback

2026-04-26 06:57:41 +00:00

docx_reviser.py

Add Track Changes architecture for draft revisions (CMP + CMPA)

2026-04-16 18:49:30 +00:00

embeddings.py

fix(mcp): eliminate "No such tool available" race at agent wakeup

2026-05-03 20:23:14 +00:00

extractor.py

fix(extractor): add regex fix for Hebrew law year gershayim corruption

2026-05-25 16:12:20 +00:00

git_sync.py

git_sync: full case-dir backup to Gitea (sweep + explicit commits)

2026-04-30 18:27:36 +00:00

halacha_extractor.py

fix(precedents): distinguish silent extraction failure from "no halachot"

2026-05-04 05:13:10 +00:00

hybrid_search.py

feat: add internal committee decisions corpus (source_kind='internal_committee')

2026-05-04 18:33:39 +00:00

internal_decisions.py

feat(migration): enrich internal committee entries — fix case_number + metadata + halachot

2026-05-04 18:59:20 +00:00

learning_loop.py

LLM session: async, 30min timeout, semantic chunking + parallel

2026-04-30 14:21:35 +00:00

lessons.py

fix: weekly-feedback-job handler writes to file only (no Paperclip issue)

2026-05-17 11:08:14 +00:00

local_classifier.py

Improve document processing pipeline and agent workflows

2026-04-09 16:45:49 +00:00

metrics.py

Add full decision writing pipeline: classify, extract, brainstorm, write, QA, export

2026-04-03 10:21:47 +00:00

practice_area.py

Add CMPA (betterment levy) training support and update methodology

2026-04-15 14:00:35 +00:00

precedent_library.py

feat: link related precedents across court instances (SCHEMA_V11)

2026-05-10 07:52:29 +00:00

precedent_metadata_extractor.py

fix(precedent-library): allow re-extraction for internal_committee rows

2026-05-06 19:44:13 +00:00

processor.py

feat(retrieval): track page_number on text chunks for multimodal hybrid boost

2026-05-03 19:49:41 +00:00

proofreader.py

Add training corpus UI with Nevo proofreading pipeline

2026-04-11 11:04:58 +00:00

qa_validator.py

LLM session: async, 30min timeout, semantic chunking + parallel

2026-04-30 14:21:35 +00:00

references_extractor.py

Fix plan regex: require numeric identifier after תב"ע

2026-04-03 10:50:56 +00:00

rerank.py

feat(retrieval): add voyage rerank-2 cross-encoder stage (feature flag)

2026-05-03 18:43:41 +00:00

research_md.py

fix: recognize extended chair-position placeholders as empty

2026-05-17 12:59:13 +00:00

style_analyzer.py

LLM session: async, 30min timeout, semantic chunking + parallel

2026-04-30 14:21:35 +00:00