Benjamin Admin 870cdc871e fix(embedding): kurze Legal-Docs behalten Sektions-Prefix (chunk_text_legal) ...

chunk_text_legal hatte einen Early-Return fuer text <= chunk_size, der den
[§ X]-Prefix uebersprang -> chunk_text_legal_structured konnte section/article
nicht extrahieren -> article="" -> (a) article_label fiel auf "BDSG" zurueck
(kein §), (b) deterministische Point-ID kollidierte (alle article="" -> gleiche
ID) -> ~die Haelfte kurzer §§ ueberschrieben sich. Fix: Early-Return traegt den
erkannten Sektions-Header als Prefix. Belegt am BDSG-§-Ingest: 44->86 distinkte
§§, §38 sauber "BDSG § 38". Wirkt nur auf KUENFTIGE Ingests (kein Re-Chunk).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

2026-06-22 23:34:11 +02:00

.claude

chore(infra): remove night-scheduler service entirely [guardrail-change]

2026-06-14 08:19:22 +02:00

.gitea/workflows

chore(infra): remove night-scheduler service entirely [guardrail-change]

2026-06-14 08:19:22 +02:00

admin-core

chore: bump next 15.1.0 → 15.5.16 across all apps (CVE-2026-44578)

2026-05-15 18:19:51 +02:00

backend-core

Remove re-export shim from keycloak_auth.py, update consumer imports

2026-04-27 00:13:30 +02:00

billing-service

…

bpmn-processes

…

consent-service

[split-required] [guardrail-change] Enforce 500 LOC budget across all services

2026-04-27 00:09:30 +02:00

control-pipeline

feat(controls): atom-inheritance schema-aware (text + jsonb source_citation)

2026-06-21 22:44:38 +02:00

docs-src

…

document-templates

…

embedding-service

fix(embedding): kurze Legal-Docs behalten Sektions-Prefix (chunk_text_legal)

2026-06-22 23:34:11 +02:00

gitea

…

legal-sources

feat(control-pipeline): incremental dedup + ENISA CRA ingestion

2026-05-18 18:21:46 +02:00

levis-holzbau

chore: bump next 15.1.0 → 15.5.16 across all apps (CVE-2026-44578)

2026-05-15 18:19:51 +02:00

marketing-website

feat(marketing): /staerken page with 7 USPs from IACE strategy — Task #19

2026-05-22 00:36:09 +02:00

nginx

feat(nginx): /mcp auf :8002 → bp-compliance-mcp (Repo-Scanner MCP-Endpoint)

2026-06-15 18:58:17 +02:00

paddleocr-service

…

pitch-deck

Add L-Bank Pre-Seed Finanzplan submissions (Base/Bear/Bull)

2026-06-02 13:25:09 +02:00

rag-service

feat(rag): regulation_short Casing-Normalisierung am Ingest-Rand

2026-06-21 18:31:45 +02:00

scripts

fix(embedding): add NIST control IDs to _SECTION_NUMBER_RE

2026-05-03 07:42:06 +02:00

vault

fix(vault): prevent CPU-burning init loop with marker file + idempotent checks

2026-05-05 11:46:16 +02:00

voice-service

[split-required] [guardrail-change] Enforce 500 LOC budget across all services

2026-04-27 00:09:30 +02:00

.env.coolify.example

…

.env.example

…

.gitignore

feat(control-pipeline): BSI QUAIDAL Clean-Room ingestion (AI Act Art. 10)

2026-05-19 13:02:49 +02:00

docker-compose.coolify.yml

…

docker-compose.hetzner.yml

chore(infra): remove night-scheduler service entirely [guardrail-change]

2026-06-14 08:19:22 +02:00

docker-compose.yml

chore(infra): remove night-scheduler service entirely [guardrail-change]

2026-06-14 08:19:22 +02:00

mkdocs.yml

…

update_pitch_deck_maschinenbau.sql

…

S

Description

No description provided

61 MiB

Languages

Python 38.2%

TypeScript 37.9%

Go 18.9%

HTML 3.2%

Shell 0.7%

Other 1.1%