✦ In dieser Sitzung haben wir den End-to-End-Test der SuperOffice-Schnittstelle erfolgreich von der automatisierten Simulation bis zum produktiven Live-Lauf
mit Echtdaten abgeschlossen.
- Implemented comprehensive E2E test covering full roundtrip and manual overrides.
- Enhanced to detect manual Vertical changes in SuperOffice and sync them to Company Explorer.
- Updated to handle industry overrides from CRM and auto-persist Person/Contact data for robust cascade updates.
1. E2E-Test erfolgreich: Das neue Test-Skript (test_e2e_full_flow.py) hat den kompletten Prozess automatisiert verifiziert:
* Provisionierung: Anlage eines Test-Unternehmens ("Klinikum Landkreis Erding (E2E Test)") über die API.
* Discovery & Analyse: Das System hat die Website gefunden, gescrapt und die Branche ("Healthcare - Hospital") korrekt
klassifiziert.
* Fehlerbehebung (Crash-Fix): Während des Tests wurde ein kritischer AttributeError im Backend identifiziert (Absturz bei
fehlenden Einheiten) und von mir behoben. Seitdem läuft die Analyse ohne Unterbrechung durch.
* Opener-Generierung: Es wurden erfolgreich zwei hoch-personalisierte Einleitungssätze (Primary & Secondary Opener) generiert.
* SuperOffice-Payload: Der finale Abgleich lieferte die korrekte Rolle ("Wirtschaftlicher Entscheider") für den
"Geschäftsführer" zurück.
Completed the GTM engine setup:\n\n- Implemented 'Dual Opener' generation (Primary/Secondary) in ClassificationService.\n- Migrated DB to support two opener fields.\n- Updated API and Frontend to handle and display both openers.\n- Fixed bug creating duplicate website_scrape entries.\n- Hardened metric extraction by improving the LLM prompt and adding content length checks.
Updated all Notion Verticals with sharpened Pains/Gains based on internal strategy (Ops vs Infra focus). Updated SuperOffice Connector README to reflect the 'Static Magic' architecture.
Implementierung der UI-Anpassungen zur Anzeige von ausstehenden Fehlerberichten (rote Flagge in der Unternehmensliste, Anzeige im Inspector) und zur Ermöglichung weiterer Fehlerberichte. Backend-APIs wurden entsprechend erweitert.
This commit resolves all outstanding issues with the AI Insights feature.
- Corrects the transcript formatting logic in to properly handle the database JSON structure, ensuring the AI receives the correct context.
- Fixes the Gemini API client by using the correct model name ('gemini-2.0-flash') and the proper client initialization.
- Updates to securely pass the API key as an environment variable to the container.
- Cleans up the codebase by removing temporary debugging endpoints.
- Adds script for programmatic updates.
- Updates documentation with troubleshooting insights from the implementation process.
- Restored missing method implementations in ClassificationService (classify, extract_metrics)
- Fixed Standardization Logic not being applied in metric cascade
- Bumped version to v0.7.4 in config.py
- Removed duplicate API endpoint in app.py
- Updated MIGRATION_PLAN.md
- **Standardization & Formula Logic:** Fixed NameError/SyntaxError in formula parser; added support for comments and capitalized placeholders.
- **Source URL Tracking:** Extended DB schema and cascade logic to store and track specific source URLs.
- **Frontend & UI:**
- Added 'Standardized Potential' display in Inspector.
- Added clickable source link with icon.
- Fixed Settings tab layout collapse (flex-shrink-0).
- **Export Capabilities:**
- Single-company JSON export now includes full quantitative metadata.
- New global CSV export endpoint /api/companies/export.
- **System Integrity:**
- Fixed Notion sync typo ('Stanardization').
- Corrected Nginx proxy routing and FastAPI route ordering.
- Ensured DB persistence via explicit docker-compose volume mapping.
- Implemented a "Re-evaluate Wikipedia" button in the UI.
- Added a backend endpoint to trigger targeted Wikipedia metric extraction.
- Hardened the LLM metric extraction prompt to prevent hallucinations.
- Corrected several database path errors that caused data loss.
- Updated application version to 0.6.4 and documented the ongoing issue.
- Fixed a critical in the company-explorer by forcing a database re-initialization with a new file (). This ensures the application code is in sync with the database schema.
- Documented the schema mismatch incident and its resolution in MIGRATION_PLAN.md.
- Restored and enhanced BUILDER_APPS_MIGRATION.md by recovering extensive, valuable content from the git history that was accidentally deleted. The guide now again includes detailed troubleshooting steps and code templates for common migration pitfalls.
- Added logic to automatically flatten list-wrapped JSON responses from LLM in Impressum extraction.
- Fixed 'Unknown Legal Name' issue by ensuring property access on objects, not lists.
- Finalized v0.3.0 features and updated documentation with Lessons Learned.
- Increased logging verbosity in to track raw input to LLM and raw LLM response.
- This helps diagnose why Impressum data extraction might be failing for specific company websites.
- Enforced fresh scrape on 'Analyze' request to bypass stale cache.
- Implemented 2-Hop Impressum scraping strategy (via Kontakt page).
- Refined numeric extraction for German locale (thousands separators).
- Updated documentation with Lessons Learned.
- Updated version to v0.3.0 (UI & Backend) to clear potential caching confusion.
- Enhanced Impressum scraper to extract VAT ID (Umsatzsteuer-ID).
- Implemented 2-Hop scraping strategy: Looks for 'Kontakt' page if Impressum isn't on the start page.
- Added VAT ID display to the Legal Data block in Inspector.
