Commit Graph

2 Commits

Author SHA1 Message Date
e09cbc112e fix: Preserve case in question IDs during parsing
All checks were successful
Deploy Development / deploy (push) Successful in 55s
Build Test / pytest-backend (push) Successful in 4s
Build Test / lint-backend (push) Successful in 0s
Build Test / build-frontend (push) Successful in 16s
Problem: Parser converted question IDs to lowercase ('qAnalyst' → 'qanalyst'),
causing normalization to fail because id_catalog lookup is case-sensitive.

Impact: All workflow question signals were lost - normalized_signals stayed empty,
so template placeholders like {{node_2.signal_qAnalyst}} remained unresolved.

Solution: Removed .lower() call in parse_decision_questions() to preserve
original case from AI response.

Root cause: Line 162 in result_container_parser.py
Fixes: Question augmentation signals not appearing in workflow end nodes
2026-04-12 14:04:14 +02:00
ca562b7130 feat: Phase 1 - Fragenergänzung + Strukturierter Container
All checks were successful
Deploy Development / deploy (push) Successful in 49s
Build Test / lint-backend (push) Successful in 0s
Build Test / build-frontend (push) Successful in 14s
Backend:
- question_augmenter.py (290 Zeilen): Hybrid-Modell für Fragenergänzungen
  * merge_question_augmentations(): Knotengebundene Fragen überschreiben Prompt-Defaults
  * augment_prompt_with_questions(): Markdown-formatierte Fragenergänzung
  * parse_question_augmentations_from_jsonb(): JSONB → QuestionAugmentation[]
- result_container_parser.py (250 Zeilen): Markdown-Sektionen-Parsing
  * parse_result_container(): Extrahiert Analysekern, Entscheidungsanteil, Begründungsanker
  * validate_decision_signal(): Normalisierung gegen answer_spectrum
  * Fallback-Parsing bei unstrukturierten Antworten
- routers/workflow_questions.py (236 Zeilen): CRUD für workflow_question_catalog
  * GET /api/workflow/questions (mit active_only Filter)
  * POST/PUT/DELETE (Admin only, Soft Delete)
- prompt_executor.py: Integration in execute_base_prompt()
  * Fragenergänzung vor LLM-Call (wenn node_questions oder catalog vorhanden)
  * Result-Container-Parsing nach LLM-Response
- main.py: Router-Registrierung (workflow_questions)

Tests:
- test_phase1_question_augmenter.py (8 Tests): Hybrid-Modell, Formatierung, JSONB-Parsing
- test_phase1_result_container_parser.py (17 Tests): Sektion-Extraktion, Decision-Parsing, Validierung

Alle 25 Unit-Tests bestanden.

version: 0.9j (backend)
module:  workflow 0.2.0

Konzept: .claude/task/Workflow_engine_prompting_engine/konzept_workflow_engine_konsolidated.md (Phase 1)
2026-04-03 18:02:25 +02:00