712 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
Benjamin Admin	cd5f986489	fix: Massnahmen-Tabelle Layout — volle Textbreite statt truncate ... Grid-Layout statt flex mit fixen Breiten. Texte umbrechen statt abschneiden. Gefaehrdung-Spalte 200px, Status 80px. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-07 16:35:09 +02:00
Benjamin Admin	a4b75dc6b1	fix: Section splitter only splits at classified headings + LLM gets full text ... Two critical fixes: 1. Section splitter: Only lines that classify as a known doc_type (cookie, social_media, dsfa, etc.) trigger section splits. Random short lines ("Typen", "Funktionale Cookies") no longer split sections — they all had blank lines before them in the extracted HTML text. 2. LLM verification: Sub-section checks now pass the full document text to the LLM, not just the section fragment. This lets the LLM find content that the section splitter missed. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-07 16:28:17 +02:00
Benjamin Admin	a1b9273649	fix: Grenzen-Formular — groessere Textfelder + vollstaendige Daten ... Allgemeine Beschreibung: 12 Zeilen (war 5) Fehlanwendungen: 10 Zeilen (war 6) Default TextArea: 6 Zeilen (war 3) Seed v2: Vollstaendige Texte + maschinenspezifische Inhalte Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-07 16:20:05 +02:00
Benjamin Admin	ac624f2e9b	feat: Umfassende Playwright-Tests fuer alle IACE Features ... Order, Grenzen, Compliance Alerts, Risk Assessment, Mitigations, CE-Akte Export, Production Lines, Normenrecherche — alle getestet. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-07 16:13:07 +02:00
Benjamin Admin	a93ba9ee40	feat: Custom Hazard Modal + Residual Risk Panel ... - CustomHazardModal: Eigene Gefaehrdung erstellen mit S/E/P/A Slidern - ResidualRiskPanel: Akzeptabel-Toggle pro Hazard + Fortschrittsbalken - RiskAssessmentTable: Accept/Reject Buttons pro Zeile integriert Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-07 16:09:50 +02:00
Benjamin Admin	5244500af6	fix: Fehlende Dateien fuer Grenzen-Formular + Report-Export ... Interview: LimitsFormSections, FormFields, SectionCard, _types Tech-File: ReportPrintView, report-types Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-07 15:56:28 +02:00
Benjamin Admin	f51671737a	fix: Correct Ollama model name + strict blank-line heading detection ... 1. LLM model: qwen3:32b → qwen3.5:35b-a3b (actual model on Mac Mini) 2. Section splitter: headings MUST be preceded by a blank line. This prevents cookie table entries ("Funktionale Cookies", "Session Cookies") from splitting the cookie section. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-07 15:53:53 +02:00
Benjamin Admin	1cc0c3d34a	feat: Auftrag-Tab + Grenzen-Formular + CE-Report-Export ... - Auftrag-Tab: Kunde, Anfrage, Angebot mit Status-Tracking - Grenzen & Verwendung: 6 Sektionen (Produktbeschreibung, Verwendung, Fehlanwendung, Grenzen, Schnittstellen, Betroffene Personen) - CE-Akte Export: PDF (window.print) + Excel (CSV) mit allen Sektionen (Normen, Gefaehrdungen, Risikobewertung, Massnahmen, Compliance) - Navigation: Auftrag als 2. Tab, Briefcase-Icon Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-07 15:44:05 +02:00
Benjamin Admin	6e71996733	fix: ComplianceAlerts API-Format Mapping ... API liefert verschachteltes Format (trigger.regulation), Frontend erwartete flaches Format. Mapping eingefuegt. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-07 15:41:25 +02:00
Benjamin Admin	4f29e5ff3c	feat: LLM verification for regex FAILs + section-split hardening ... Path to 100% correctness: Regex finds 80%, LLM catches the rest. 1. LLM verification (llm_verify.py): - Every regex FAIL is re-checked by Qwen (qwen3:32b) - Binary YES/NO question with evidence extraction - Overturned checks marked with [LLM] prefix in matched_text - Graceful fallback if LLM unavailable 2. Section splitter hardening: - Short lines (<16 chars) only treated as headings if preceded by blank line — prevents table column headers ("Funktion", "Speicherdauer") from splitting cookie sections - Fixes IHK cookie section: 288 words → full section 3. DSFA documentation patterns expanded: - Recognizes "4.) Ergebnis:" numbered result sections - Matches risk assessment conclusions Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-07 15:34:07 +02:00
Benjamin Admin	1d75bbf4eb	feat: IACE Navigation-Struktur — Grenzen-Tab + Zusatzmodule ... - 'Grenzen & Verwendung' als neuen Tab eingefuegt (Schritt 3 CE-Prozess) - Klassifikation + Monitoring als 'Zusatzmodule' separiert - chat-Icon fuer Interview/Grenzen Tab Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-07 15:17:56 +02:00
Benjamin Admin	a3287cd5e6	feat: HTML email report with hints + fix duplicate Social Media sections ... 1. Email report now renders as styled HTML (matching frontend design): - Progress bars (green=completeness, blue=correctness) - Hierarchical L1→L2 check display - Red hint boxes under failed checks explaining what to fix - Matched text evidence for passed checks 2. Section splitter deduplicates: two "Social Media" headings on the same page are merged into one section instead of creating duplicates. 3. Extracted report builder to agent_doc_check_report.py (175 LOC) to keep routes file under 500 LOC (386 LOC). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-07 15:13:00 +02:00
Benjamin Admin	56892cf7dc	feat: CE × Compliance Crossover Engine ... Automatische Erkennung von DSGVO/AI Act/CRA/NIS2/Data Act Implikationen bei CE-Gefaehrdungen. 50 Trigger-Mappings auf Hazard-Patterns → Compliance-Module mit Modul-Links. - compliance_triggers.go: 50 Pattern→Regulation Mappings - compliance_crossover.go: Engine die Projekt-Hazards gegen Trigger prueft - iace_handler_compliance.go: GET /compliance-triggers API - ComplianceAlerts.tsx: Frontend Alert-Panel auf Projekt-Uebersicht Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-07 15:07:22 +02:00
Benjamin Admin	fa4fd87102	fix: 7 regex bugs from IHK Konstanz ground truth analysis ... Fixes based on manual verification of all 30 failed checks: 1. Cookie table: recognize "folgende cookies" + column headers as text 2. Cookie names: add JSESSIONID, cookieinfo, et_id, BT_* patterns 3. Essential justified: match "sitzung zuordnen", "betrieb der website" 4. Social bookmarks: recognize as 2-click alternative 5. DSFA plural: "kanaelen" now matches alongside "kanal" 6. Section splitter: skip-headings no longer lose subsequent text (Risikoabwaegung section was cut from DSFA, losing risk scores) 7. Cookie legal basis: accept Art. 6(1)(f) in cookie context Reduces false positives from 7 to ~1-2 for IHK Konstanz test case. Ground truth table: zeroclaw/docs/ground-truth-ihk-konstanz.md Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-07 14:51:09 +02:00
Benjamin Admin	f59f810638	chore: LOC-Exceptions fuer IACE Pattern-Datendateien ... [guardrail-change] Hazard-Pattern-Dateien sind reine Datentabellen (85 Patterns × 12 Zeilen). Aufsplitten wuerde die Zuordnung pro Themenbereich zerstoeren. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-07 14:36:51 +02:00
Benjamin Admin	86504ef280	feat: 1000 unique Hazard-Patterns erreicht! ... 336 neue Patterns (HP1000-HP1335): - Mechanisch detailliert (85): Quetschen, Scheren, Einziehen pro Koerperteil - Elektrisch/Thermisch/Chemisch (85): Verbrennung, Einatmen, Hautkontakt - Software/Organisation/Umgebung (85): SPS, Sensor, Aktor, HMI, Notfall - Lebenszyklus/Verkettung/Retrofit (81): Beschaffung, Manipulation, Dritte Gesamtstand: 1000 Patterns + 751 Normen + 200 Massnahmen Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-07 14:29:10 +02:00
Benjamin Admin	3d7b09bcef	feat: Massnahmen-Bibliothek auf 200 erweitert (3-Stufen) ... 60 Design + 80 Schutz + 60 Information — alle mit Normenreferenzen. Subtypes: geometry, force_energy, material, ergonomics, control_design, fixed_guard, movable_guard, electro_sensitive, emergency_stop, electrical/thermal/fluid protection, extraction, signage, manual, training, ppe, organizational, marking. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-07 14:23:15 +02:00
Benjamin Admin	71802614cc	feat: Batch F patterns + engine cleanup ... Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-07 14:15:37 +02:00
Benjamin Admin	30236638ed	feat: 664 unique Hazard-Patterns + Test-Fix ... Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-07 14:05:58 +02:00
Benjamin Admin	293c58d0dd	feat: Add actionable hints to all 138 compliance checks ... Each check now has a "hint" field explaining what is missing and what the customer should do to fix it. Hints are shown in the frontend below failed checks in red text. Examples: - "Bei Verarbeitung auf Basis von Art. 6(1)(f) muss dokumentiert werden, warum Ihr berechtigtes Interesse die Rechte der Betroffenen ueberwiegt." - "Die ladungsfaehige Anschrift fehlt. Erforderlich: Strasse, Hausnummer, PLZ und Ort." Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-07 14:05:01 +02:00
Benjamin Admin	912684644e	feat: Hazard-Patterns auf 725+ — Split-Dateien von Batch B integriert ... Neue Dateien: packaging, medical_pressure, specific_machines2 Split: food_pkg aufgeteilt in food_processing + packaging Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-07 14:01:46 +02:00
Benjamin Admin	2b2a20cc6d	feat: Hazard-Patterns auf 725 erweitert ... 4 neue Pattern-Dateien: - Workshop (65): Stolpern, Ergonomie, Chemie, Brand, Strahlung, Biologie - Maintenance Extended (65): LOTO, Einrichten, Stoerung, Transport, Inbetriebnahme - Specific Machines (55): Druckgeraete, Wind, Solar, Batterie, Fahrtreppen, Schwimmbad - Cyber/AI Extended (65): Software-Fehler, Ransomware, KI-Bias, OPC-UA, HMI 751 Normen + 725 Patterns = umfassende CE-Bibliothek Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-07 13:55:15 +02:00
Benjamin Admin	05839e36aa	feat: Hazard-Patterns auf 475 erweitert (Ziel: 1000) ... 8 neue Pattern-Dateien fuer: - Aufzuege (25), AGV/Landmaschinen (30), Lebensmittel/Verpackung (35) - Laser/Medizin/Druck (40), Bau/Krane (20), Forst/Foerderer (31) - Kunststoff/Metall (30), Schweissen/Glas/Textil (30) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-07 13:31:23 +02:00
Benjamin Admin	870953f579	fix: PLZ regex matches lowercase text and D-78467 format ... Patterns ran on text.lower() but searched [A-Z] — changed to [a-z]. Also accept D-12345 prefix (common German format). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-07 13:28:00 +02:00
Benjamin Admin	1005ba0398	feat: Normen-Bibliothek auf 751 Normen finalisiert ... Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-07 13:24:33 +02:00
Benjamin Admin	fb6192d92d	feat: Normen-Bibliothek auf 747 Normen — Ziel 700 uebertroffen ... 24 Dateien, 747 Normen mit Abschnittsreferenzen und Beuth-URLs. Abdeckung: Maschinenbau, Elektrik, Hydraulik, Holz, Metall, Kunststoff, Lebensmittel, Verpackung, Textil, Landmaschinen, Erdbau, Krane, Aufzuege, Foerdertechnik, AGV, Medizin, Labor, Pharma, Energie, Bau, Bergbau, Forst, PSA, ATEX, EMV, Spielplatz, Fitness, Schwimmbad, Glas, Leder, Papier, Airport, Waescherei, Feuerwehr, Seilbahnen, Fahrgeschaefte. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-07 13:18:25 +02:00
Benjamin Admin	8849c396b5	fix: Show L2 detail checks always visible (no extra click needed) ... L2 checks were hidden behind a second click on L1 items. Now they render inline below their L1 parent, always visible when the document card is expanded. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-07 13:16:04 +02:00
Benjamin Admin	ba9558384f	feat: Normen-Bibliothek auf 620+ erweitert + wave3 fixes ... Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-07 13:13:08 +02:00
Benjamin Admin	2e1e18d853	feat: Normen-Bibliothek auf 617 erweitert (Ziel: 700) ... Wave 3: +161 Normen (456 → 617) - Serien-Lücken geschlossen (EN 1870, EN 474, EN 1034, EN 81, ISO 4254) - Glas, Leder, Backwaren, Tabak, Medizin (IEC 60601), Labor, Feuerwehr - Spielplatz, Fitness, Schwimmbad, HVAC, Kältetechnik - PSA (Schuhe, Handschuhe, Augenschutz, Gehörschutz, Atemschutz) - Leitern, Gerüste, Drahtseile, Gasgeräte, Messtechnik Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-07 13:04:22 +02:00
Benjamin Admin	9bc0f321e0	feat: Normen-Bibliothek auf 456 erweitert + UX-Verbesserungen ... - Normen: 215 → 456 (Werkzeugmaschinen, Förder/AGV, Verfahrenstechnik, Bau/Bergbau, Holz/Papier, Airport, Wäscherei, B2-Erweiterung) - Maßnahmen: Accordion-Tabellenansicht mit Batch-Verifizierung - Hazards: Risikobewertung als Default-View, KI-Button entfernt - Normenrecherche: Pflicht-Erklärung, + Norm hinzufügen Feld - Produktionslinien: Inline-Erstellungsformular mit Projekt-Zuordnung - Playwright Tests angepasst Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-07 12:45:15 +02:00
Benjamin Admin	97a52533a8	Merge remote gitea/main — resolve conflicts keeping local (origin) state ... Local origin is 20+ commits ahead of remote gitea. All conflicts resolved by keeping HEAD (our version) which includes the full 56→138 check expansion and doc_checks package split. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-07 12:40:23 +02:00
Benjamin Admin	b363c28539	feat: Add 76 Level-2 regex checks for document correctness verification ... Split dsi_document_checker.py (466 LOC) into doc_checks/ package (9 files). Two-pass L1→L2 logic: L1 checks "Is it mentioned?", L2 checks "Is it correct?" (e.g. controller has full address, specific Art. 6 lit., concrete time periods). 138 total checks (62 L1 + 76 L2) across 7 doc types: - DSE Art. 13: 31, Impressum §5 TMG: 16, Cookie §25 TDDDG: 15 - Widerruf §355: 15, AGB §305ff: 21, Social Media Art. 26: 20, DSFA Art. 35: 18 Frontend: hierarchical L1→L2 display with dual progress bars (green=completeness, blue=correctness). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-07 12:37:03 +02:00
Benjamin Admin	3c12e06faf	feat: Fix DSFA dedup + expand all checklists to 56 total checks ... Fixes: - 'Risikoabwaegung' is sub-section of DSFA → added to SKIP_HEADINGS - 'Social Media' standalone heading → recognized as social_media DSE - Removed 'risikobew' from DSFA pattern (was too broad) Expanded checklists: - Widerruf: 4→7 checks (+Empfaenger, kein Grund, §312k Button) - AGB: 4→9 checks (+Zahlung, Lieferung, Gewaehrleistung, Kuendigung, Datenschutz) - Social Media: +1 (Social Bookmarks) - DSFA: +1 (LFDI Richtlinie) Total: 47→56 Regex-Checks across 7 document types: DSI=9, Cookie=5, Social Media=10, DSFA=8, Impressum=6, Widerruf=7, AGB=9 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-07 11:55:29 +02:00
Benjamin Admin	58234ac18b	fix: DSFA must be matched before social_media in SECTION_TYPE_MAP ... 'Datenschutzfolgeabschätzung...Social Media' was matching as social_media (Art. 26) instead of dsfa (Art. 35) because the social_media pattern 'datenschutz.*social media' matched first. Fixed: DSFA patterns checked before social_media patterns. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-07 11:35:10 +02:00
Benjamin Admin	4642abba23	feat: Expand Social Media (10 checks) + DSFA (8 checks) checklists ... Art. 26 Joint Controller (10 checks, was 7): + Auflistung der genutzten Plattformen + Rechtsgrundlage (Art. 6) + Social Bookmarks vs. Plugins Hinweis Improved: broader patterns for joint parties, contact point, data types DSFA Art. 35 (8 checks, was 5): + Schwellwertanalyse / Auslösepruefung + Beruecksichtigung Landesbehörden-Richtlinie (LFDI) + Dokumentation der Ergebnisse Improved: IHK-specific patterns (Kanäle, systematische Beobachtung, geringer Umfang, sensitive Daten) Total: 40 → 47 Regex-Checks across all document types. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-07 11:17:16 +02:00
Benjamin Admin	e7f2f98da3	feat: IACE CE-Compliance Module — Normen, Risikobewertung, Production Lines ... Major features: - 215 norms library with section references + Beuth URLs (A/B1/B2/C norms) - 173 hazard patterns with detail fields (scenario, trigger, harm, zone) - Deterministic pattern matching: Component × Lifecycle × Pattern cross-product - SIL/PL auto-calculation from S×E×P risk graph - Risk assessment table with editable S/E/P dropdowns - Production Line Dashboard with animated station flow (Running Dots) - IACE process flow + norms coverage on start page - Non-blocking cookie banner, ProcessFlow SSR fix - 104 Playwright E2E tests passing Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-07 10:53:26 +02:00
Benjamin Admin	3853a0838a	feat: Art. 26 Joint Controller + DSFA checklists for Social Media sections ... New checklists: - JOINT_CONTROLLER_CHECKLIST (Art. 26 DSGVO, 7 checks): Joint parties, arrangement, contact point, processing split, data categories, third-country transfer (USA), rights - DSFA_CHECKLIST (Art. 35 DSGVO, 5 checks): Description, necessity, risk assessment, measures, DSB involvement Section detection: 'Datenschutzerklaerung fuer Social Media' → social_media, 'Datenschutzfolgeabschaetzung/Risikoanalyse' → dsfa classify_document_type: DSFA and social_media detected before generic DSE Frontend: DOC_TYPES dropdown + ChecklistView labels updated Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-07 10:49:32 +02:00
Benjamin Admin	5188411828	disable: Control Library checks until doc-check Master Controls are ready ... 8 false positives from generic canonical_controls. Regex checks (9+5) are accurate. Re-enable when ~80 specific doc-check controls exist. See INSTRUCTION-master-controls-for-doc-check.md Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-07 10:28:25 +02:00
Benjamin Admin	45446aef16	fix: 8 quality + UX improvements ... 1. Cookie 'Zwecke' false positive: added 'um...zu', 'dienen', 'helfen', 'ermöglichen' patterns — catches purpose descriptions without 'Zweck' 2. Kurzhinweis: added empty all_checks for short documents (<200 words) 3. Bezeichnungsfeld: placeholder shows 'Version / Stand' for typed docs, 'Dokumentname' for 'Sonstiges' 4. DocCheckTab state persistence: entries + results survive navigation 5. DocCheck history: saves each check with date, doc count, findings 6. History display: 'Letzte Pruefungen' section at bottom of tab 7. ChecklistView: shows 'X von Y Pruefpunkten bestanden' per document 8. Results persist in localStorage across page navigation Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-07 09:37:47 +02:00
Benjamin Admin	e19d9ca532	docs: Master Controls spec for document checker — 80-100 specific check criteria ... Detailed requirements for the pipeline session: - Binary yes/no check_question per control - Concrete pass_criteria + fail_criteria (not 'check completeness') - correction_template from our Template Generator - 8 document types: DSI, Cookie, Impressum, Widerruf, AGB, DSFA, AVV, Loeschkonzept - ~80-100 total controls (not 25K generic ones) - Examples for DSI, Cookie, Impressum with exact field expectations Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-07 07:53:36 +02:00
Benjamin Admin	a680276c86	fix: Filter controls by test_procedure content — eliminates governance false positives ... Only use controls whose test_procedure mentions document-type-specific terms: - DSI: test_procedure must contain 'datenschutzerkl' or 'art. 13/14' - Cookie: must contain 'cookie', 'einwilligung', 'consent' - Impressum: must contain 'impressum' This filters out internal governance controls (Datenmodelle, Infrastruktur) that are irrelevant for public document checks. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-06 20:42:35 +02:00
Benjamin Admin	fa45b5793c	feat: Control Library check via SQL (canonical_controls) instead of Qdrant ... Complete rewrite of rag_document_checker.py: - Queries canonical_controls table (294K controls, 10K data_protection) - Filters by category + title keywords per document type - Uses test_procedure field as actual check instructions - Regex pre-check extracts key terms from procedure → fast match - LLM fallback only for regex misses (saves tokens) - /no_think prefix for direct JSON output SQL approach advantages: - Structured data with test_procedure, pass_criteria, fail_criteria - Category filtering (data_protection, compliance, governance) - No Qdrant API key issues - Controls are actual check criteria, not general legal texts Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-06 20:26:56 +02:00
Benjamin Admin	7e7f31c344	disable: RAG checks until Master Controls (G1 Decision Trace) are ready ... Current 144K controls are general legal texts, not specific check criteria. RAG integration code stays (rag_document_checker.py), just disabled in the doc-check endpoint. Re-enable when G1-G4 block is complete and 25K Master Controls with Decision Trace are available. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-06 17:11:58 +02:00
Benjamin Admin	6da36d87c2	fix: Robust JSON parsing for LLM responses — handles unquoted keys, fallback extraction ... LLM returns {fulfilled: true} instead of {"fulfilled": true}. Now fixes unquoted keys, True→true, and falls back to text-based boolean extraction when JSON parsing fails entirely. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-06 15:18:52 +02:00
Benjamin Admin	e50c4d659e	fix: Disable Qwen thinking mode for RAG checks (/no_think prefix) ... Qwen 3.5 uses all tokens for thinking, leaving response empty. Using /no_think prefix to get direct JSON output. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-06 15:12:51 +02:00
Benjamin Admin	9f16e6d535	fix: Read Qwen response from 'thinking' field when 'response' is empty ... Qwen 3.5 with latest Ollama returns structured thinking in separate 'thinking' field, leaving 'response' empty. Now checks both fields. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-06 15:07:09 +02:00
Benjamin Admin	1ff34227bf	debug: Add logging to RAG check integration ... Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-06 14:57:30 +02:00
Benjamin Admin	f4374cfe8d	feat: Semantic Qdrant search — embed query via bge-m3, vector search in local Qdrant ... Replaces scroll+filter approach with proper semantic search: 1. Embed query via bp-core-embedding-service (bge-m3, 1024 dim) 2. Vector search in Qdrant (bp_compliance_datenschutz + bp_compliance_gesetze) 3. Sort by cosine similarity score 4. No API key needed — local Qdrant on Mac Mini Falls back gracefully: SDK first, then semantic Qdrant, then empty. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-06 14:46:06 +02:00
Benjamin Admin	7b8440191e	fix: Better error logging + increase LLM timeout to 120s for RAG check ... Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-06 14:33:58 +02:00
Benjamin Admin	510f513811	fix: Qdrant search uses chunk_text + section/category filter ... Payload structure: chunk_text (not text), section (Article 13), category, regulation_id. Scrolls 100 points per collection, filters client-side against regulation keywords. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-05-06 14:28:32 +02:00