chore(agents): rewrite all agent definitions for current architecture

Major updates across all 8 agents:
- Architecture: no more blender-renderer HTTP (port 8100), all via render-worker Celery
- Task location: backend/app/domains/pipeline/tasks/ (not backend/app/tasks/)
- Roles: global_admin/tenant_admin hierarchy (not just admin)
- Queues: thumbnail_rendering on render-worker (not worker-thumbnail)
- USD pipeline awareness: pxr/usd-core, partKey, primvars, FlattenLayerStack

New: Planner <-> Implementer failure loop:
- implement.md: Failure Protocol — [BLOCKED] tag + report to planner, stop
- plan.md: 'When Called After Failure' section — refine failing task, add
  root cause + revised approach + unblock code snippet
- review.md: on blocking issues, also update plan.md with [BLOCKED] tag

Agent-specific updates:
- plan.md: ROADMAP.md as primary reference, current pipeline description,
  USD decisions documented
- implement.md: render-worker subprocess chain, PipelineLogger rule,
  MinIO/storage_key conventions
- review.md: USD checklist section, updated pipeline checks (no STL,
  no HTTP renderer), storage_key absolute path check
- check.md: render-worker health gate, removed worker-thumbnail refs
- debug-render.md: complete rewrite — no HTTP endpoint testing, direct
  subprocess testing, updated symptom table with USD/GMSH errors
- db-migrate.md: planned migration table (060-065), current migration
  number (059), USD-related patterns
- frontend.md: role hierarchy, sceneManifest.ts reference, X-Tenant-ID
  interceptor note
- excel-import.md: minor cleanup, consistent format

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

.claude/commands/excel-import.md

@@ -1,109 +1,117 @@
-# Excel-Import-Agent
+# Excel Import Agent
 
-Du bist spezialisiert auf den Excel-Import-Parser des Schaeffler Automat Projekts. Du untersuchst Import-Probleme, ergänzt neue Felder und passt die Parsing-Logik an.
+You are a specialist for the Excel import parser in the Schaeffler Automat project. You investigate import problems, add new fields, and adjust parsing logic.
 
-## Übersicht Excel-Parser
+## Parser Overview
 
-**Datei**: `backend/app/services/excel_parser.py`
+**File**: `backend/app/services/excel_parser.py`
 
-Der Parser liest Schaeffler-Auftrags-Excel-Dateien (7 Kategorien) und extrahiert Produktdaten.
+The parser reads Schaeffler order Excel files (7 product categories) and extracts product data.
 
-### Header-Erkennung (header-driven, Phase 14)
-- Sucht in den ersten 5 Zeilen nach `"Ebene1"` in einer beliebigen Spalte
-- Baut dynamische `column_map` über `HEADER_FIELD_MAP` (normalisierte Header-Texte → Feldnamen)
-- Altes Format: "Ebene1" in Spalte 0 → Komponenten ab Spalte 11
-- Neues Format: "Arbeitspaket" in Spalte 0, "Ebene1" in Spalte 1 → Komponenten ab Spalte 12
+### Header Detection
+- Searches rows 0–4 for `"Ebene1"` in any column
+- Builds a dynamic `column_map` from `HEADER_FIELD_MAP` (normalized header text → field name)
+- Old format: `"Ebene1"` in column 0 → components from column 11
+- New format: `"Arbeitspaket"` in column 0, `"Ebene1"` in column 1 → components from column 12
 
-### Erkannte Kategorien
+### Recognized Categories
 `TRB`, `Kugellager`, `CRB`, `Gleitlager`, `SRB_TORB`, `Linear_schiene`, `Anschlagplatten`
 
-### Wichtige ParsedRow-Felder
+### Key ParsedRow Fields
 - `pim_id`, `produkt_baureihe`, `gewaehltes_produkt`
-- `name_cad_modell` — wird für STEP-Datei-Matching genutzt
+- `name_cad_modell` — used for STEP file matching
 - `kategorie`, `category_key`, `arbeitspaket`
-- `gewuenschte_bildnummer` — Varianten-Differenziator
-- `cad_part_materials` — Rohes Material-Mapping für Render
-- `components` — Teileliste mit Anzahl + Materialien
+- `gewuenschte_bildnummer` — variant differentiator
+- `cad_part_materials` — raw material mapping dict `{part_name: material_name}`
+- `components` — component list with quantity + materials
 
-### Material-Mapping Sheet
-`_parse_material_mapping(wb)` — liest separates Sheet "Materialmapping":
-- Gibt `[{display_name, render_name}]` zurück
-- Wird beim Upload als Material-Aliases geseedet
+### Material Mapping Sheet
+`_parse_material_mapping(wb)` reads the "Materialmapping" sheet:
+- Returns `[{display_name, render_name}]`
+- Seeded as Material aliases on upload
 
-## Diagnose bei Import-Problemen
+## Diagnose Import Problems
 
 ```bash
-# Logs des Upload-Endpunkts
-docker compose logs -f backend | grep "excel\|upload\|import"
+# Backend upload logs
+docker compose logs -f backend | grep -i "excel\|upload\|import\|parse"
 
-# Test-Import im Container
+# Test parse in container
 docker compose exec backend python3 -c "
 from app.services.excel_parser import parse_excel_file
 rows = parse_excel_file('/app/uploads/test.xlsx')
+print(f'Rows parsed: {len(rows)}')
 for r in rows[:3]:
-    print(r)
+    print(vars(r))
 "
+
+# Check material aliases seeded
+docker compose exec postgres psql -U schaeffler -d schaeffler -c "
+SELECT m.name, ma.alias FROM materials m
+JOIN material_aliases ma ON ma.material_id = m.id
+LIMIT 20;"
 ```
 
-### Typische Probleme
+## Common Problems
 
-| Problem | Mögliche Ursache | Diagnose |
+| Problem | Likely Cause | Diagnosis |
 |---|---|---|
-| Alle Rows leer | Header-Erkennung schlägt fehl | `"Ebene1"` in Zeilen 0-4 suchen |
-| Falsches Feld gemappt | Header-Text stimmt nicht mit `HEADER_FIELD_MAP` überein | Header-Normalisierung prüfen (strip + lower) |
-| Kategorie nicht erkannt | `_detect_row_category()` findet kein Match | `kategorie`-Spalte Rohwert prüfen |
-| Material-Aliases nicht geseedet | Materialmapping-Sheet fehlt oder anders benannt | Sheet-Namen im Excel prüfen |
-| Varianten fehlen | `gewuenschte_bildnummer` nicht unterschiedlich | Rohdaten prüfen |
+| All rows empty | Header detection fails | Look for `"Ebene1"` in rows 0–4 |
+| Wrong field mapped | Header text doesn't match `HEADER_FIELD_MAP` | Check normalization (strip + lower) |
+| Category not recognized | `_detect_row_category()` finds no match | Print raw `kategorie` column value |
+| Material aliases not seeded | "Materialmapping" sheet missing or renamed | Check sheet names in Excel file |
+| Variants missing | `gewuenschte_bildnummer` not distinct | Check raw data values |
+| `cad_part_materials` empty | Material mapping columns not found | Verify column headers match `HEADER_FIELD_MAP` |
 
-## Neues Feld zum Parser hinzufügen
+## Adding a New Field
 
-1. **`HEADER_FIELD_MAP`** erweitern:
+1. **Extend `HEADER_FIELD_MAP`**:
    ```python
    HEADER_FIELD_MAP = {
        ...
-       "neuer header text": "neues_feld",
+       "new header text": "new_field_name",
    }
    ```
 
-2. **`ParsedRow`-Dataclass** erweitern:
+2. **Extend `ParsedRow` dataclass**:
    ```python
    @dataclass
    class ParsedRow:
        ...
-       neues_feld: str | None = None
+       new_field_name: str | None = None
    ```
 
-3. **Verwendung in Import-Logik** (`uploads.py` oder `product_service.py`):
-   - Wo wird das Feld gespeichert? Neues DB-Feld? Oder in `components` JSONB?
-   - Migration nötig? → `/db-migrate` Agent nutzen
+3. **Decide where to store it** (`uploads.py` or `product_service.py`):
+   - New DB column → use `/db-migrate` agent
+   - Already in `components` JSONB → add to the dict
 
-## Neue Kategorie hinzufügen
+## Adding a New Category
 
-1. Kategorie-Regex in `_detect_row_category()` ergänzen
-2. `CATEGORY_KEYS` dict erweitern
-3. Falls spezifische Spalten-Logik: in `_parse_row_components()` behandeln
-4. `compatible_categories` auf betroffenen `OutputType`-Einträgen in der DB setzen
+1. Extend category regex in `_detect_row_category()`
+2. Extend `CATEGORY_KEYS` dict
+3. If category needs specific column logic: handle in `_parse_row_components()`
+4. Set `compatible_categories` on affected `OutputType` entries in the DB
 
-## Test-Workflow
+## Full Test Workflow
 
 ```python
-# Einzelne Excel-Datei testen
 docker compose exec backend python3 -c "
 import json
 from app.services.excel_parser import parse_excel_file
 rows = parse_excel_file('/app/uploads/[filename].xlsx')
-print(f'Rows: {len(rows)}')
+print(f'Total rows: {len(rows)}')
 for r in rows:
     print(json.dumps({
         'pim_id': r.pim_id,
         'produkt_baureihe': r.produkt_baureihe,
         'category_key': r.category_key,
         'name_cad_modell': r.name_cad_modell,
-        'materials_count': len(r.cad_part_materials or {})
+        'materials_count': len(r.cad_part_materials or {}),
+        'new_field': getattr(r, 'new_field_name', None),
     }, indent=2))
 "
 ```
 
-## Abschluss
+## Completion
 
-Berichte welche Felder korrekt/falsch geparst wurden und was geändert wurde.
+Report which fields were correctly/incorrectly parsed and what was changed.