Implement Chain Workbench and Vault Triage features in Mindnet plugin

- Introduced new workflows for Chain Workbench and Vault Triage, enhancing user capabilities for managing template matches and identifying chain gaps.
- Added commands for opening the Chain Workbench and scanning the vault for chain gaps, improving the overall functionality of the plugin.
- Updated documentation to include detailed instructions for the new workflows, ensuring users can effectively utilize the features.
- Enhanced the UI for both the Chain Workbench and Vault Triage Scan, providing a more intuitive user experience.
- Implemented tests for the new functionalities to ensure reliability and accuracy in various scenarios.

docs/01_Benutzerhandbuch.md

@@ -264,6 +264,54 @@ Inhalt mit Links: [[Note1]] und [[Note2]]
    - Verfügbare Actions auswählen
    - Automatische Behebung
 
+### Workflow 5: Chain Workbench verwenden (Neu in 0.5.x)
+
+1. **Section öffnen:**
+   - Cursor in relevante Section positionieren
+
+2. **Chain Workbench öffnen:**
+   - Command: "Mindnet: Chain Workbench (Current Section)"
+   - Modal zeigt alle Template Matches
+
+3. **Matches analysieren:**
+   - Filter nach Status (complete, near_complete, partial, weak)
+   - Suche nach Template-Name
+   - Match auswählen → Details anzeigen
+
+4. **Todos bearbeiten:**
+   - Todo auswählen
+   - Action wählen (z.B. "Insert Edge", "Create Note", "Promote Candidate")
+   - Apply → Workbench aktualisiert sich automatisch
+
+5. **Wiederholen:**
+   - Weitere Todos bearbeiten
+   - Status verbessert sich nach jedem Apply
+
+### Workflow 6: Vault Triage Scan (Neu in 0.5.x)
+
+1. **Scan starten:**
+   - Command: "Mindnet: Scan Vault for Chain Gaps"
+   - Modal öffnet sich
+
+2. **Scan durchführen:**
+   - Klicke "Start Scan"
+   - Progress wird angezeigt
+   - Scan kann unterbrochen werden
+
+3. **Backlog durchsuchen:**
+   - Filter nach Status, Gap-Typen
+   - Suche nach File, Heading, Template
+   - Sortierung: near_complete zuerst
+
+4. **Items bearbeiten:**
+   - "Open Workbench" → öffnet Datei und Workbench
+   - "Deprioritize" → markiert als nicht fokussiert
+   - Items bleiben im Backlog (werden gefiltert)
+
+5. **Resume:**
+   - Scan kann fortgesetzt werden (wenn unterbrochen)
+   - State wird gespeichert
+
 ### Workflow 3: Unresolved Link → Note erstellen
 
 1. **Link erstellen:**
@@ -323,6 +371,8 @@ Inhalt mit Links: [[Note1]] und [[Note2]]
 | Command | Beschreibung | Wann verwenden |
 |---------|--------------|----------------|
 | **Mindnet: Inspect Chains (Current Section)** | Analysiert kausale Ketten | Chain-Analyse durchführen |
+| **Mindnet: Chain Workbench (Current Section)** | Workbench für alle Template Matches mit Todos | Chain-Gaps identifizieren und beheben |
+| **Mindnet: Scan Vault for Chain Gaps** | Scannt gesamten Vault nach Chain-Gaps | Vault-weites Backlog erstellen |
 | **Mindnet: Fix Findings (Current Section)** | Behebt Findings automatisch | Findings automatisch beheben |
 | **Mindnet: Validate current note** | Validiert aktuelle Note (Lint) | Note auf Fehler prüfen |
 

docs/02_concepts/03_chain_identification_and_matching.md

@@ -0,0 +1,393 @@
+# Chain-Identifikation und Template Matching
+
+## Übersicht
+
+Das System identifiziert und füllt Chains durch einen mehrstufigen Prozess:
+
+1. **Graph-Indexierung**: Erfassung aller Edges (Kanten) im lokalen Subgraph
+2. **Candidate-Node-Sammlung**: Identifikation potenzieller Knoten für Template-Slots
+3. **Template Matching**: Backtracking-Algorithmus zur optimalen Slot-Zuordnung
+4. **Link-Validierung**: Prüfung, ob Edges zwischen zugewiesenen Slots existieren
+5. **Scoring & Confidence**: Bewertung der Match-Qualität
+
+---
+
+## 1. Graph-Indexierung
+
+### Edge-Erfassung
+
+Der **Chain Inspector** (`src/analysis/chainInspector.ts`) erfasst alle Edges im lokalen Subgraph:
+
+- **Current Section**: Die aktuelle Section (file + heading)
+- **Incoming Edges**: Edges, die zur aktuellen Section zeigen
+- **Outgoing Edges**: Edges, die von der aktuellen Section ausgehen
+- **Neighbor Notes**: Verbundene Notes werden geladen, um den Subgraph zu erweitern
+
+### Edge-Scopes
+
+Edges können drei Scopes haben:
+
+- **`section`**: Section-spezifisch (`[[Note#Heading]]`)
+- **`note`**: Note-weit (`[[Note]]` ohne Heading)
+- **`candidate`**: In "## Kandidaten" Zone
+
+### Filterung
+
+Edges werden basierend auf `InspectorOptions` gefiltert:
+
+- `includeNoteLinks`: Ob Note-Scope Edges einbezogen werden
+- `includeCandidates`: Ob Candidate Edges einbezogen werden
+- `maxDepth`: Maximale Tiefe für Path-Traversal
+
+---
+
+## 2. Candidate-Node-Sammlung
+
+### Prozess (`buildCandidateNodes`)
+
+Für jeden Edge im Subgraph werden **Candidate Nodes** erstellt:
+
+1. **Source Nodes**: Alle Knoten, von denen Edges ausgehen
+2. **Target Nodes**: Alle Knoten, zu denen Edges zeigen
+3. **Note-Type-Extraktion**: Frontmatter `type:` wird aus jeder Note extrahiert
+4. **Deduplizierung**: Gleiche Knoten (file + heading) werden nur einmal erfasst
+
+### Node-Repräsentation
+
+```typescript
+interface CandidateNode {
+  nodeKey: {
+    file: string;
+    heading: string | null;
+  };
+  noteType: string; // z.B. "insight", "decision", "experience"
+}
+```
+
+### Maximale Anzahl
+
+Standardmäßig werden maximal **30 Candidate Nodes** gesammelt (konfigurierbar).
+
+---
+
+## 3. Template Matching
+
+### Template-Definition (`chain_templates.yaml`)
+
+Jedes Template definiert:
+
+- **Slots**: Positionen in der Chain mit erlaubten Note-Types
+- **Links**: Erwartete Verbindungen zwischen Slots mit erlaubten Edge-Roles
+
+**Beispiel: `loop_learning`**
+
+```yaml
+slots:
+  - id: experience
+    allowed_node_types: [experience, journal, event]
+  - id: learning
+    allowed_node_types: [insight, principle, value, belief, skill, trait]
+  - id: behavior
+    allowed_node_types: [habit, decision, task]
+  - id: feedback
+    allowed_node_types: [experience, journal, event, state]
+
+links:
+  - from: experience
+    to: learning
+    allowed_edge_roles: [causal, provenance, influences]
+  - from: learning
+    to: behavior
+    allowed_edge_roles: [influences, enables_constraints, causal]
+  - from: behavior
+    to: feedback
+    allowed_edge_roles: [causal, influences]
+```
+
+### Backtracking-Algorithmus (`findBestAssignment`)
+
+Der Algorithmus findet die **beste Slot-Zuordnung** durch systematisches Ausprobieren:
+
+1. **Slot-Filterung**: Für jeden Slot werden nur Candidate Nodes gefiltert, die den `allowed_node_types` entsprechen
+2. **Backtracking**: Rekursives Durchprobieren aller möglichen Zuordnungen
+3. **Distinct Nodes**: Jeder Knoten kann nur einmal zugeordnet werden (wenn `distinct_nodes: true`)
+4. **Scoring**: Jede vollständige Zuordnung wird bewertet
+5. **Best Match**: Die Zuordnung mit dem höchsten Score wird zurückgegeben
+
+### Slot-Zuordnung
+
+```typescript
+function backtrack(assignment: Map<string, CandidateNode>, slotIndex: number) {
+  // Wenn alle Slots zugeordnet sind:
+  if (slotIndex >= slots.length) {
+    const result = scoreAssignment(...); // Bewerte Zuordnung
+    if (result.score > bestScore) {
+      bestMatch = result; // Speichere besten Match
+    }
+    return;
+  }
+  
+  // Probiere jeden passenden Candidate für diesen Slot
+  for (const candidate of slotCandidates.get(slot.id)) {
+    if (!alreadyAssigned(candidate)) {
+      assignment.set(slot.id, candidate);
+      backtrack(assignment, slotIndex + 1); // Rekursiv weiter
+      assignment.delete(slot.id); // Backtrack
+    }
+  }
+  
+  // Auch: Slot leer lassen (für unvollständige Chains)
+  backtrack(assignment, slotIndex + 1);
+}
+```
+
+---
+
+## 4. Link-Validierung
+
+### Edge-Suche (`findEdgeBetween`)
+
+Für jedes Template-Link wird geprüft, ob ein Edge zwischen den zugewiesenen Slots existiert:
+
+1. **Node-Keys**: `fromKey = "file:heading"`, `toKey = "file:heading"`
+2. **Edge-Suche**: Durchsuche `allEdges` nach passendem Edge
+3. **Canonicalisierung**: Edge-Typ wird auf Canonical gemappt (via `edge_vocabulary.md`)
+4. **Role-Mapping**: Canonical Edge-Typ wird auf Role gemappt (via `chain_roles.yaml`)
+5. **Role-Validierung**: Prüfe, ob Edge-Role in `allowed_edge_roles` enthalten ist
+
+### Role-Evidence
+
+Wenn ein Link erfüllt ist, wird **Role Evidence** gespeichert:
+
+```typescript
+roleEvidence.push({
+  from: "learning",        // Slot-ID (nicht Dateipfad!)
+  to: "behavior",          // Slot-ID
+  edgeRole: "causal",      // Role aus chain_roles.yaml
+  rawEdgeType: "resulted_in" // Original Edge-Typ im Vault
+});
+```
+
+**Wichtig**: `roleEvidence` verwendet **Slot-IDs**, nicht Dateipfade!
+
+---
+
+## 5. Scoring & Confidence
+
+### Scoring (`scoreAssignment`)
+
+**Slot-Scoring**:
+- Jeder zugewiesene Slot: **+2 Punkte**
+
+**Link-Scoring**:
+- Erfüllter Link (mit erlaubter Role): **+10 Punkte**
+- Fehlender Link (wenn `required_links: true`): **-5 Punkte**
+- Falsche Role (wenn `required_links: true`): **-5 Punkte**
+
+### Confidence-Berechnung
+
+Die **Confidence** wird nach dem Matching berechnet:
+
+1. **`weak`**: Wenn `slotsComplete === false` (fehlende Slots)
+2. **`confirmed`**: Wenn `slotsComplete === true` UND `linksComplete === true` UND mindestens eine causal-ish Role Evidence
+3. **`plausible`**: Sonst (Slots vollständig, aber Links unvollständig oder keine causal Roles)
+
+**Causal-ish Roles**: `["causal", "influences", "enables_constraints"]` (konfigurierbar in `chain_templates.yaml`)
+
+### Completeness
+
+- **`slotsComplete`**: `missingSlots.length === 0`
+- **`linksComplete`**: `satisfiedLinks === requiredLinks`
+
+---
+
+## 6. Template-Matching-Profile
+
+### Profile-Definition
+
+Profile steuern die Matching-Strenge:
+
+**`discovery`** (schreibfreundlich):
+```yaml
+required_links: false  # Links sind optional
+min_slots_filled_for_gap_findings: 2
+min_score_for_gap_findings: 8
+```
+
+**`decisioning`** (strikt):
+```yaml
+required_links: true  # Links sind Pflicht
+min_slots_filled_for_gap_findings: 3
+min_score_for_gap_findings: 18
+```
+
+### Profile-Auflösung
+
+1. **Settings**: Plugin-Einstellung `templateMatchingProfile`
+2. **Template**: Template-spezifische `matching.required_links`
+3. **Defaults**: `defaults.matching.required_links`
+
+---
+
+## 7. Beispiel: Loop Learning Match
+
+### Input
+
+- **Current Section**: `Tests/03_insight_transformation.md#Kern`
+- **Edges im Subgraph**: 8 Edges (1 current, 7 neighbors)
+- **Candidate Nodes**: 4 Nodes (experience, learning, behavior, feedback)
+
+### Template
+
+```yaml
+name: loop_learning
+slots: [experience, learning, behavior, feedback]
+links:
+  - experience → learning
+  - learning → behavior
+  - behavior → feedback
+```
+
+### Matching-Prozess
+
+1. **Slot-Zuordnung** (Backtracking):
+   - `experience` → `Tests/02_event_trigger_detail.md#Detail` (noteType: `event`)
+   - `learning` → `Tests/03_insight_transformation.md#Kern` (noteType: `insight`)
+   - `behavior` → `Tests/04_decision_outcome.md#Entscheidung` (noteType: `decision`)
+   - `feedback` → `Tests/01_experience_trigger.md#Kontext` (noteType: `experience`)
+
+2. **Link-Validierung**:
+   - `experience → learning`: ❌ Kein Edge gefunden
+   - `learning → behavior`: ✅ Edge `resulted_in` mit Role `causal` gefunden
+   - `behavior → feedback`: ❌ Kein Edge gefunden
+
+3. **Scoring**:
+   - Slots: 4 × 2 = **8 Punkte**
+   - Links: 1 × 10 = **10 Punkte**
+   - **Gesamt: 18 Punkte**
+
+4. **Resultat**:
+   ```json
+   {
+     "templateName": "loop_learning",
+     "score": 18,
+     "slotsComplete": true,
+     "linksComplete": false,
+     "satisfiedLinks": 1,
+     "requiredLinks": 3,
+     "confidence": "plausible",
+     "roleEvidence": [
+       {
+         "from": "learning",
+         "to": "behavior",
+         "edgeRole": "causal",
+         "rawEdgeType": "resulted_in"
+       }
+     ]
+   }
+   ```
+
+---
+
+## 8. Wichtige Konzepte
+
+### Slot-IDs vs. Dateipfade
+
+- **Slot-IDs**: Template-interne Bezeichner (`"learning"`, `"behavior"`)
+- **Dateipfade**: Vault-Pfade (`"Tests/03_insight_transformation.md"`)
+- **roleEvidence** verwendet Slot-IDs, nicht Dateipfade!
+
+### Canonicalisierung
+
+- **Intern**: Edge-Typen werden auf Canonical gemappt (für Analyse)
+- **Vault**: Original Edge-Typen (Aliase) bleiben unverändert
+- **Schreiben**: Plugin schreibt keine Canonicals, nur User-gewählte Typen
+
+### Distinct Nodes
+
+Wenn `distinct_nodes: true`:
+- Jeder Knoten kann nur **einmal** pro Template zugeordnet werden
+- Verhindert zirkuläre Zuordnungen
+
+### Edge-Target-Resolution
+
+Edges können verschiedene Pfad-Formate verwenden:
+- Vollständig: `Tests/03_insight_transformation.md`
+- Basename: `03_insight_transformation`
+- Wikilink: `[[03_insight_transformation]]`
+
+Das System normalisiert alle Formate für konsistente Matching.
+
+---
+
+## 9. Integration mit Chain Workbench
+
+Der **Chain Workbench** nutzt die Template Matches, um:
+
+1. **Todos zu generieren**:
+   - `missing_slot`: Fehlende Slot-Zuordnungen
+   - `missing_link`: Fehlende Links zwischen Slots
+   - `weak_roles`: Links mit schwachen (nicht-causalen) Roles
+
+2. **Status zu berechnen**:
+   - `complete`: Slots + Links vollständig
+   - `near_complete`: 1-2 Links fehlen oder 1 Slot fehlt
+   - `partial`: Mehrere Lücken
+   - `weak`: Nur structural/temporal Roles, keine causal Roles
+
+3. **Actions anzubieten**:
+   - `insert_edge_forward`: Edge einfügen (von Slot A nach Slot B)
+   - `link_existing`: Bestehenden Knoten verlinken
+   - `create_note_via_interview`: Neue Note für Slot erstellen
+
+---
+
+## 10. Konfigurationsdateien
+
+### `chain_templates.yaml`
+
+Definiert Template-Strukturen:
+- Slots mit erlaubten Note-Types
+- Links mit erlaubten Edge-Roles
+- Profile (discovery, decisioning)
+
+### `chain_roles.yaml`
+
+Mappt Edge-Typen auf Roles:
+- `causal`: Direkte Kausalität
+- `influences`: Indirekte Einflussnahme
+- `enables_constraints`: Ermöglicht/Einschränkt
+- `structural`: Strukturelle Beziehung
+- `temporal`: Zeitliche Beziehung
+
+### `edge_vocabulary.md`
+
+Definiert Canonical Edge-Typen und Aliase:
+- Canonical: `resulted_in`
+- Aliase: `führt_zu`, `resultiert_in`, etc.
+
+### `graph_schema.md`
+
+Definiert Note-Type-Kompatibilität:
+- Welche Edge-Typen sind typisch für `insight → decision`?
+- Welche Edge-Typen sind verboten?
+
+---
+
+## Zusammenfassung
+
+Das System identifiziert Chains durch:
+
+1. **Graph-Indexierung**: Erfassung aller Edges im lokalen Subgraph
+2. **Candidate-Sammlung**: Identifikation potenzieller Knoten
+3. **Backtracking-Matching**: Optimale Slot-Zuordnung
+4. **Link-Validierung**: Prüfung vorhandener Edges
+5. **Scoring**: Bewertung der Match-Qualität
+
+Das Ergebnis sind **Template Matches** mit:
+- Slot-Zuordnungen (welche Knoten in welchen Slots)
+- Link-Status (welche Links erfüllt/fehlend)
+- Confidence (confirmed/plausible/weak)
+- Role Evidence (welche Edges welche Roles haben)
+
+Diese Matches werden dann im **Chain Workbench** verwendet, um konkrete Todos und Actions zu generieren.

docs/03_Entwicklerhandbuch.md

@@ -151,9 +151,9 @@ npm run lint
 ### Development Workflow
 
 1. **Code ändern** in `src/`
-2. **Watch Mode** läuft (`npm run dev`)
+2. **Watch Mode** läuft (`npm.cmd run dev`)
 3. **Automatisches Rebuild** bei Dateiänderungen
-4. **Deploy lokal** (`npm run deploy:local` oder `npm run build:deploy`)
+4. **Deploy lokal** (`npm.cmd run deploy:local` oder `npm.cmd run build:deploy`)
 5. **Obsidian Plugin reload** (disable/enable)
 6. **Testen**
 

docs/08_Testing_Chain_Workbench.md

@@ -0,0 +1,309 @@
+# Testing Chain Workbench + Vault Triage (0.5.x)
+
+Diese Anleitung beschreibt, wie du die neuen Chain Workbench und Vault Triage Features in Obsidian testen kannst.
+
+## Voraussetzungen
+
+1. **Node.js** installiert (LTS Version empfohlen)
+2. **Obsidian** installiert
+3. **Vault** mit Mindnet-konfigurierten Dateien:
+   - `Dictionary/chain_templates.yaml`
+   - `Dictionary/chain_roles.yaml`
+   - `Dictionary/edge_vocabulary.md`
+   - `Dictionary/analysis_policies.yaml` (optional)
+   - `Dictionary/interview_config.yaml` (für Interview-Features)
+
+## Build & Installation
+
+### 1. Dependencies installieren
+
+```bash
+cd c:\Dev\cursor\mindnet_obsidian
+npm install
+```
+
+### 2. Plugin bauen
+
+```bash
+npm run build
+```
+
+Dies erstellt `main.js` im Projekt-Root.
+
+### 3. Plugin in Obsidian installieren
+
+**Option A: Lokales Deployment (empfohlen für Entwicklung)**
+
+```powershell
+npm run deploy:local
+```
+
+Dies kopiert automatisch `main.js`, `manifest.json` und `styles.css` (falls vorhanden) in dein Test-Vault.
+
+**Option B: Manuell**
+
+1. Öffne dein Obsidian Vault
+2. Gehe zu `.obsidian/plugins/`
+3. Erstelle Ordner `mindnet-causal-assistant` (falls nicht vorhanden)
+4. Kopiere folgende Dateien:
+   - `main.js` (aus Projekt-Root)
+   - `manifest.json` (aus Projekt-Root)
+   - `styles.css` (falls vorhanden)
+
+### 4. Plugin aktivieren
+
+1. Öffne Obsidian Settings
+2. Gehe zu **Community plugins**
+3. Aktiviere **Mindnet Causal Assistant**
+4. Stelle sicher, dass die Dictionary-Pfade korrekt konfiguriert sind:
+   - Edge Vocabulary Path: `Dictionary/edge_vocabulary.md`
+   - Chain Templates Path: `Dictionary/chain_templates.yaml`
+   - Chain Roles Path: `Dictionary/chain_roles.yaml`
+   - Interview Config Path: `Dictionary/interview_config.yaml`
+
+## Testing Chain Workbench
+
+### Schritt 1: Test-Vault vorbereiten
+
+Erstelle oder öffne eine Note mit:
+- Mindestens einer Section (H2-Überschrift)
+- Einigen Edges (z.B. in Semantic Mapping Block)
+- Optional: Candidate Edges in "## Kandidaten" Zone
+
+**Beispiel-Note:**
+
+```markdown
+---
+id: test_note_001
+type: concept
+---
+
+# Test Note
+
+## Kontext
+
+Dies ist eine Test-Section mit einigen Links.
+
+> [!abstract]- 🕸️ Semantic Mapping
+>> [!edge] caused_by
+>> [[Target Note 1]]
+
+## Kandidaten
+
+> [!abstract]
+>> [!edge] impacts
+>> [[Target Note 2]]
+```
+
+### Schritt 2: Chain Workbench öffnen
+
+1. Öffne die Test-Note im Editor
+2. Setze den Cursor in eine Section (z.B. "Kontext")
+3. Öffne Command Palette (`Ctrl+P` / `Cmd+P`)
+4. Suche nach: **"Mindnet: Chain Workbench (Current Section)"**
+5. Klicke auf den Command
+
+### Schritt 3: Workbench UI verwenden
+
+**Erwartetes Verhalten:**
+
+- Modal öffnet sich mit:
+  - Links: Liste aller Template Matches
+  - Rechts: Details des ausgewählten Matches
+- Filter nach Status verfügbar
+- Suche nach Template-Name funktioniert
+
+**Zu testen:**
+
+1. **Match-Liste**:
+   - Alle Matches werden angezeigt (nicht nur Top-1)
+   - Status-Icons sind korrekt (✓, ~, ○, ⚠)
+   - Sortierung: near_complete zuerst
+
+2. **Match-Details**:
+   - Slots-Info korrekt angezeigt
+   - Links-Info korrekt angezeigt
+   - Todos werden aufgelistet
+
+3. **Todo-Actions**:
+   - Klicke auf "Insert Edge" für `missing_link` Todo
+   - Wähle Zone (Section / Note-Verbindungen / Kandidaten)
+   - Wähle Edge-Typ
+   - Prüfe: Edge wurde eingefügt
+   - Prüfe: Workbench aktualisiert sich nach Apply
+
+4. **Candidate Promotion**:
+   - Wenn Candidate Edge vorhanden, sollte `candidate_cleanup` Todo erscheinen
+   - Klicke auf "Promote"
+   - Prüfe: Candidate wurde zu explizitem Edge befördert
+   - Prüfe: Candidate wurde aus Kandidaten-Zone entfernt (wenn `keepOriginal=false`)
+
+## Testing Interview-Orchestrierung
+
+### Schritt 1: Missing Slot Todo erstellen
+
+1. Öffne Chain Workbench für eine Section mit fehlendem Slot
+2. Wähle einen Match mit `missing_slot` Todo
+
+### Schritt 2: Create Note via Interview
+
+1. Klicke auf "Create Note" Button
+2. **Erwartetes Verhalten**:
+   - Profile Selection Modal öffnet sich
+   - Nur erlaubte Profile werden angezeigt (gefiltert nach `allowedNodeTypes`)
+   - User wählt Profile, Titel, Ordner
+3. **Nach Auswahl**:
+   - Note wird erstellt mit Frontmatter
+   - Zonen werden erstellt (je nach Settings)
+   - Interview Wizard startet automatisch
+4. **Nach Interview-Abschluss**:
+   - Soft-Validation prüft requiredEdges
+   - Notice zeigt fehlende Edges (falls vorhanden)
+
+**Zu testen:**
+
+- Profile-Filterung funktioniert
+- Note wird korrekt erstellt
+- Interview startet
+- Soft-Validation zeigt korrekte Meldungen
+
+## Testing Vault Triage Scan
+
+### Schritt 1: Scan starten
+
+1. Öffne Command Palette
+2. Suche nach: **"Mindnet: Scan Vault for Chain Gaps"**
+3. Klicke auf den Command
+
+### Schritt 2: Scan durchführen
+
+**Erwartetes Verhalten:**
+
+- Modal öffnet sich
+- "Start Scan" Button verfügbar
+- Nach Klick: Scan läuft durch alle Dateien
+- Progress wird angezeigt
+
+**Zu testen:**
+
+1. **Scan-Prozess**:
+   - Progress wird aktualisiert
+   - Aktuelle Datei wird angezeigt
+   - Scan kann unterbrochen werden (Cancel)
+
+2. **Backlog-Liste**:
+   - Items werden nach Scan angezeigt
+   - Sortierung: near_complete zuerst
+   - Gap-Counts sind korrekt
+
+3. **Filter**:
+   - Status-Filter funktioniert
+   - Gap-Typ-Filter funktioniert (missing_slot, missing_link, etc.)
+   - Suche funktioniert (File, Heading, Template)
+
+4. **Actions**:
+   - "Open Workbench" öffnet Datei und Workbench
+   - "Deprioritize" markiert Item als deprioritized
+   - Item verschwindet nicht, sondern wird gefiltert
+
+5. **Resume**:
+   - Schließe Modal während Scan läuft
+   - Öffne Scan erneut
+   - "Resume Scan" sollte verfügbar sein
+   - Scan setzt fort
+
+## Troubleshooting
+
+### Plugin lädt nicht
+
+- Prüfe: `main.js` existiert im Plugin-Ordner
+- Prüfe: `manifest.json` ist vorhanden
+- Prüfe: Console (F12) für Fehler
+- Prüfe: Plugin ist in Settings aktiviert
+
+### Chain Workbench zeigt keine Matches
+
+- Prüfe: Chain Templates sind geladen (Settings → Dictionary Paths)
+- Prüfe: Section hat Edges oder Links
+- Prüfe: Console für Fehler
+- Prüfe: Template Matching Profile ist korrekt
+
+### Interview startet nicht
+
+- Prüfe: Interview Config ist geladen
+- Prüfe: Profile existiert für gewählten noteType
+- Prüfe: Settings → `autoStartInterviewOnCreate` ist aktiviert
+
+### Vault Scan ist langsam
+
+- Normal für große Vaults
+- Scan kann unterbrochen werden
+- Progress wird gespeichert für Resume
+
+### Edge wird nicht eingefügt
+
+- Prüfe: Zone existiert oder wird erstellt
+- Prüfe: Section hat Semantic Mapping Block oder wird erstellt
+- Prüfe: Console für Fehler
+- Prüfe: File-Berechtigungen
+
+## Debug-Modus
+
+Für detaillierte Logs:
+
+1. Öffne Obsidian Console (F12)
+2. Aktiviere Debug-Logging in Settings:
+   - Settings → Mindnet Settings → Debug Logging
+
+**Wichtige Console-Logs:**
+
+- `[Chain Workbench]` - Workbench-Operationen
+- `[Vault Triage Scan]` - Scan-Operationen
+- `[Chain Inspector]` - Template Matching
+- `[Workbench]` - Todo-Generierung
+
+## Beispiel-Workflow
+
+1. **Erstelle Test-Note** mit unvollständiger Chain:
+   ```markdown
+   ## Kontext
+   
+   Content hier.
+   
+   > [!abstract]- 🕸️ Semantic Mapping
+   >> [!edge] caused_by
+   >> [[Note A]]
+   ```
+
+2. **Öffne Chain Workbench** für diese Section
+
+3. **Erwartung**: 
+   - Match für Template (z.B. `trigger_transformation_outcome`)
+   - Status: `partial` oder `near_complete`
+   - Todos: `missing_slot` für "transformation" oder "outcome"
+
+4. **Teste Actions**:
+   - Klicke "Create Note" → Interview startet
+   - Oder: Klicke "Insert Edge" → Edge wird eingefügt
+
+5. **Nach Apply**:
+   - Workbench aktualisiert sich automatisch
+   - Match-Status verbessert sich (z.B. `partial` → `near_complete`)
+
+## Nächste Schritte
+
+Nach erfolgreichem Test:
+
+1. Teste mit realen Vault-Daten
+2. Prüfe Performance bei großen Vaults
+3. Teste Edge-Cases (leere Sections, fehlende Zonen, etc.)
+4. Gib Feedback zu UX/UI
+
+## Bekannte Einschränkungen
+
+- `link_existing` ist noch Placeholder (fügt Link ein, aber Slot-Assignment erfordert Re-Run)
+- Interview Quick-Insert (requiredEdges) ist vorbereitet, aber noch nicht vollständig integriert
+- `insert_edge_inverse` noch nicht implementiert
+- `change_edge_type` noch nicht implementiert
+
+Diese Features werden in späteren Iterationen vervollständigt.

docs/09_Workbench_Analysis_Basis.md

@@ -0,0 +1,278 @@
+# Chain Workbench - Analyse-Basis und Erweiterungen
+
+> **Version:** 0.5.x  
+> **Stand:** 2025-01-XX  
+> **Zielgruppe:** Entwickler, Architekten
+
+---
+
+## Übersicht
+
+Die Chain Workbench (0.5.x) basiert **hauptsächlich** auf den Analysen aus Chain Inspector (0.4.x), erweitert diese aber um zusätzliche Heuristiken und granularere Todo-Generierung.
+
+---
+
+## Basis: Chain Inspector 0.4.x Analysen
+
+### Template Matching (0.4.x)
+
+Die Workbench nutzt direkt die **Template Matches** aus Chain Inspector:
+
+- **`TemplateMatch` Interface:**
+  - `templateName`: Name des Templates
+  - `score`: Match-Score (+10 pro Link, +2 pro Slot, -5 pro fehlendem required Link)
+  - `slotAssignments`: Map von Slot-ID → Node-Referenz
+  - `missingSlots`: Array von fehlenden Slot-IDs
+  - `satisfiedLinks`: Anzahl erfüllter Links
+  - `requiredLinks`: Anzahl erforderlicher Links
+  - `roleEvidence`: Array von Edge-Role-Evidence
+  - `slotsComplete`: Boolean
+  - `linksComplete`: Boolean
+  - `confidence`: "confirmed" | "plausible" | "weak"
+
+**Quelle:** `src/analysis/chainInspector.ts` → `inspectChains()` → `matchTemplates()`
+
+### Findings aus 0.4.x (aktuell NICHT verwendet, aber sollten integriert werden)
+
+**Status:** Die Findings aus Chain Inspector werden aktuell **nicht** in der Workbench verwendet, obwohl sie aufwendig getestet wurden und wertvolle Informationen liefern.
+
+**Findings aus 0.4.x:**
+- `missing_edges` - Section hat Content aber keine Edges
+- `one_sided_connectivity` - Nur incoming oder nur outgoing edges
+- `only_candidates` - Nur Candidate-Edges, keine expliziten
+- `dangling_target` - Target-Datei existiert nicht
+- `dangling_target_heading` - Target-Heading existiert nicht
+- `no_causal_roles` - Section hat Edges aber keine kausalen Rollen
+- `missing_slot_<slotId>` - Template-basiert: Slot fehlt (aggregiert)
+- `missing_link_constraints` - Template-basiert: Links fehlen (aggregiert)
+- `weak_chain_roles` - Template-basiert: Nur non-causal Rollen (aggregiert)
+
+**Warum aktuell nicht verwendet?**
+- Die Workbench fokussiert sich aktuell nur auf **Template-basierte Todos**
+- Findings sind teilweise **aggregiert** (z.B. "missing_slot_trigger" für alle Matches)
+- Workbench benötigt **granulare Todos** pro Match (z.B. "missing_slot_trigger" für jeden Match einzeln)
+- Workbench benötigt **konkrete Actions** (z.B. `insert_edge_forward`, `create_note_via_interview`)
+
+**Sollten integriert werden:**
+Die Findings könnten als **zusätzliche Todos** integriert werden:
+- `dangling_target` → Todo mit Action `create_missing_note` oder `retarget_link`
+- `dangling_target_heading` → Todo mit Action `create_missing_heading` oder `retarget_to_existing_heading`
+- `only_candidates` → Todo mit Action `promote_all_candidates` oder `create_explicit_edges`
+- `missing_edges` → Todo mit Action `add_edges_to_section`
+- `no_causal_roles` → Todo ähnlich wie `weak_roles`, aber section-weit (nicht template-basiert)
+- `one_sided_connectivity` → Informatives Todo (keine Action, nur Hinweis)
+
+**Vorteil der Integration:**
+- Nutzung der **getesteten Heuristiken** aus 0.4.x
+- **Vollständigere Analyse** (nicht nur Template-basiert)
+- **Konsistenz** zwischen Chain Inspector und Workbench
+
+---
+
+## Neue Analysen in 0.5.x
+
+### 1. Status-Berechnung (`statusCalculator.ts`)
+
+**Neu in 0.5.x:** Berechnet `MatchStatus` basierend auf Slot/Link-Erfüllung:
+
+- **`complete`**: `slotsFilled == slotsTotal && linksSatisfied == linksRequired`
+- **`near_complete`**: 
+  - `slotsFilled == slotsTotal && (linksRequired - linksSatisfied) in {1,2}`
+  - ODER `(slotsTotal - slotsFilled) == 1 && linksSatisfied == linksRequired`
+- **`weak`**: Match vorhanden, aber nur structural/temporal Rollen (keine causal)
+- **`partial`**: Sonstige Fälle mit mindestens einer Lücke
+
+**Basis:** TemplateMatch aus 0.4.x, aber **neue Heuristik** für Status-Kategorisierung.
+
+### 2. Granulare Todo-Generierung (`todoGenerator.ts`)
+
+**Neu in 0.5.x:** Generiert konkrete Todos pro Match:
+
+#### `missing_slot` Todo
+- **Basis:** `match.missingSlots` aus TemplateMatch
+- **Erweiterung:** 
+  - Pro Slot ein Todo (nicht aggregiert)
+  - Enthält `allowedNodeTypes` für Interview-Filterung
+  - Enthält Actions: `["link_existing", "create_note_via_interview"]`
+
+#### `missing_link` Todo
+- **Basis:** Template-Links aus `template.links` + `match.slotAssignments`
+- **Erweiterung:**
+  - Prüft, ob beide Slots gefüllt sind, aber Link fehlt
+  - Enthält `fromNodeRef` und `toNodeRef` (konkrete Referenzen)
+  - Enthält `suggestedEdgeTypes` aus `chain_roles.yaml`
+  - Enthält Actions: `["insert_edge_forward", "insert_edge_inverse", "choose_target_anchor"]`
+
+#### `weak_roles` Todo
+- **Basis:** `match.roleEvidence` aus TemplateMatch
+- **Erweiterung:**
+  - Prüft, ob alle Rollen structural/temporal sind (keine causal)
+  - Enthält Liste von `edges` mit `currentRole` und `suggestedRoles`
+  - Enthält Actions: `["change_edge_type"]`
+
+#### `candidate_cleanup` Todo (NEU)
+- **Basis:** Candidate-Edges aus `graphIndex` + `missing_link` Todos
+- **Vollständig neu:**
+  - Findet Candidate-Edges, die zu `missing_link` Requirements passen
+  - **Relation-Equality-Check:** Prüft, ob bereits ein confirmed Edge für dieselbe Relation existiert
+  - Wenn ja → kein Todo (verhindert Duplikate)
+  - Wenn nein → Todo mit `promote_candidate` Action
+
+**Relation-Equality-Logik:**
+```typescript
+// Prüft:
+// 1. Direction match (from → to)
+// 2. Node-Refs match (file + heading)
+// 3. Canonical Edge-Type match (via edge_vocabulary.md)
+```
+
+### 3. Effective Required Links Resolution
+
+**Neu in 0.5.x:** Resolved `required_links` Flag mit Priorität:
+
+1. `template.matching?.required_links` (höchste Priorität)
+2. `profile.required_links`
+3. `defaults.matching?.required_links`
+4. Fallback: `false`
+
+**Basis:** TemplateMatch nutzt bereits `requiredLinks`, aber Workbench benötigt explizite Resolution für UI-Darstellung.
+
+---
+
+## Vergleich: Findings vs. Todos
+
+| Aspekt | Chain Inspector 0.4.x (Findings) | Chain Workbench 0.5.x (Todos) |
+|--------|----------------------------------|-------------------------------|
+| **Granularität** | Aggregiert (pro Template-Typ) | Granular (pro Match, pro Slot/Link) |
+| **Format** | `Finding` Interface (code, severity, message) | `WorkbenchTodoUnion` Interface (type, actions, refs) |
+| **Actions** | Keine (nur Informativ) | Konkrete Actions (`insert_edge_forward`, etc.) |
+| **Basis** | Template Matches + Gap-Heuristiken | Template Matches + zusätzliche Analysen |
+| **Verwendung** | Console-Output, Fix Findings Command | Workbench UI, interaktive Bearbeitung |
+
+---
+
+## Abhängigkeiten
+
+### Direkte Abhängigkeiten (0.4.x)
+
+1. **`TemplateMatch`** aus `chainInspector.ts`
+   - Wird direkt verwendet für Status-Berechnung und Todo-Generierung
+
+2. **`ChainTemplatesConfig`** aus `dictionary/types.ts`
+   - Wird verwendet für Slot/Link-Definitionen und `allowed_node_types`
+
+3. **`ChainRolesConfig`** aus `dictionary/types.ts`
+   - Wird verwendet für `suggestedEdgeTypes` in `missing_link` Todos
+
+4. **`EdgeVocabulary`** aus `vocab/types.ts`
+   - Wird verwendet für Canonical-Type-Resolution (Relation-Equality)
+
+5. **`IndexedEdge[]`** aus `graphIndex.ts`
+   - Wird verwendet für Candidate/Confirmed-Edge-Trennung
+
+### Indirekte Abhängigkeiten
+
+1. **Template Matching Algorithmus** (0.4.x)
+   - Backtracking-Algorithmus für Slot-Assignment
+   - Scoring-Mechanismus (+10 pro Link, +2 pro Slot, -5 pro fehlendem required Link)
+
+2. **Edge-Role-Mapping** (0.4.x)
+   - `chain_roles.yaml` → Edge-Types → Roles
+   - Wird verwendet für `weak_roles` Detection
+
+---
+
+## Neue Heuristiken (nicht in 0.4.x)
+
+### 1. Relation-Equality-Check
+
+**Zweck:** Verhindert Duplikate bei Candidate-Cleanup.
+
+**Logik:**
+- Prüft, ob bereits ein confirmed Edge für dieselbe Relation existiert
+- Relation = (fromNodeRef, toNodeRef, canonicalEdgeType)
+- Wenn ja → kein `candidate_cleanup` Todo
+
+**Implementierung:** `todoGenerator.ts` → `checkRelationExists()`
+
+### 2. Status-Kategorisierung
+
+**Zweck:** Priorisierung von Matches in Workbench UI.
+
+**Logik:**
+- `complete` → höchste Priorität (grün)
+- `near_complete` → hohe Priorität (gelb)
+- `partial` → mittlere Priorität (orange)
+- `weak` → niedrige Priorität (rot)
+
+**Implementierung:** `statusCalculator.ts` → `calculateMatchStatus()`
+
+### 3. Effective Required Links Resolution
+
+**Zweck:** Korrekte Darstellung von Link-Requirements in UI.
+
+**Logik:**
+- Resolved `required_links` Flag mit Priorität (template > profile > defaults)
+- Beeinflusst, ob `missing_link` Todos generiert werden
+
+**Implementierung:** `statusCalculator.ts` → `getEffectiveRequiredLinks()`
+
+---
+
+## Zusammenfassung
+
+### Basierend auf 0.4.x
+
+✅ **Template Matches** - Direkt verwendet  
+✅ **Slot-Assignments** - Direkt verwendet  
+✅ **Missing Slots** - Direkt verwendet  
+✅ **Role Evidence** - Direkt verwendet  
+✅ **Edge-Role-Mapping** - Direkt verwendet  
+✅ **Canonical Edge Types** - Direkt verwendet  
+
+### Neu in 0.5.x
+
+🆕 **Status-Berechnung** - Neue Heuristik  
+🆕 **Granulare Todos** - Pro Match, pro Slot/Link  
+🆕 **Candidate-Cleanup** - Relation-Equality-Check  
+🆕 **Effective Required Links** - Prioritäts-Resolution  
+🆕 **Action-System** - Konkrete Actions pro Todo  
+
+### Nicht verwendet aus 0.4.x (sollten integriert werden)
+
+⚠️ **Findings** - Werden aktuell nicht verwendet, sollten aber integriert werden  
+⚠️ **Gap-Heuristiken** - Werden aktuell nicht verwendet, sollten aber integriert werden  
+⚠️ **Dangling Target Checks** - Werden aktuell nicht verwendet, sollten aber integriert werden  
+
+**Empfehlung:** Die Findings sollten als **zusätzliche Todos** in die Workbench integriert werden, um die getesteten Heuristiken zu nutzen und eine vollständigere Analyse zu bieten.  
+
+---
+
+## Fazit
+
+Die Chain Workbench (0.5.x) basiert **hauptsächlich** auf den Template Matches aus Chain Inspector (0.4.x), erweitert diese aber um:
+
+1. **Granulare Todo-Generierung** (pro Match, pro Slot/Link)
+2. **Status-Kategorisierung** (complete, near_complete, partial, weak)
+3. **Candidate-Cleanup-Heuristik** (Relation-Equality-Check)
+4. **Action-System** (konkrete Actions pro Todo)
+
+**Aktueller Stand:**
+Die Workbench verwendet aktuell **nur** die Template Matches aus 0.4.x, nicht die Findings. Dies ermöglicht eine **interaktive Bearbeitung** mit konkreten Actions.
+
+**Empfohlene Erweiterung:**
+Die Findings aus 0.4.x sollten als **zusätzliche Todos** integriert werden, um:
+- Die **getesteten Heuristiken** zu nutzen
+- Eine **vollständigere Analyse** zu bieten (nicht nur Template-basiert)
+- **Konsistenz** zwischen Chain Inspector und Workbench zu gewährleisten
+
+**Nächste Schritte:**
+1. Findings aus `report.findings` in `buildWorkbenchModel` einlesen
+2. Findings zu Todos konvertieren (mit entsprechenden Actions)
+3. Findings-Todos zu den Template-basierten Todos hinzufügen
+4. UI erweitern, um beide Todo-Typen anzuzeigen
+
+---
+
+**Letzte Aktualisierung:** 2025-01-XX  
+**Version:** 0.5.x

docs/10_Workbench_Findings_Integration.md

@@ -0,0 +1,342 @@
+# Chain Workbench - Findings Integration (Vorschlag)
+
+> **Status:** Vorschlag für zukünftige Implementierung  
+> **Stand:** 2025-01-XX  
+> **Zielgruppe:** Entwickler
+
+---
+
+## Problemstellung
+
+Die Chain Workbench (0.5.x) verwendet aktuell **nur** Template Matches aus Chain Inspector (0.4.x), nicht aber die **Findings** und **Gap-Heuristiken**, die aufwendig getestet wurden.
+
+**Verlorene Informationen:**
+- `dangling_target` - Target-Datei existiert nicht
+- `dangling_target_heading` - Target-Heading existiert nicht
+- `only_candidates` - Nur Candidate-Edges, keine expliziten
+- `missing_edges` - Section hat Content aber keine Edges
+- `no_causal_roles` - Section hat Edges aber keine kausalen Rollen
+- `one_sided_connectivity` - Nur incoming oder nur outgoing edges
+
+---
+
+## Lösungsvorschlag
+
+### 1. Findings zu Todos konvertieren
+
+Erweitere `todoGenerator.ts` um eine Funktion `generateFindingsTodos()`:
+
+```typescript
+/**
+ * Generate todos from Chain Inspector findings.
+ */
+export function generateFindingsTodos(
+  findings: Finding[],
+  allEdges: IndexedEdge[],
+  context: { file: string; heading: string | null }
+): WorkbenchTodoUnion[] {
+  const todos: WorkbenchTodoUnion[] = [];
+
+  for (const finding of findings) {
+    switch (finding.code) {
+      case "dangling_target":
+        // Find edge with dangling target
+        const danglingEdge = allEdges.find(
+          (e) => e.target.file === finding.evidence?.file
+        );
+        if (danglingEdge) {
+          todos.push({
+            type: "dangling_target",
+            id: `dangling_target_${finding.evidence?.file}`,
+            description: finding.message,
+            priority: finding.severity === "error" ? "high" : "medium",
+            targetFile: danglingEdge.target.file,
+            targetHeading: danglingEdge.target.heading,
+            sourceEdge: {
+              file: "sectionHeading" in danglingEdge.source 
+                ? danglingEdge.source.file 
+                : danglingEdge.source.file,
+              heading: "sectionHeading" in danglingEdge.source
+                ? danglingEdge.source.sectionHeading
+                : null,
+            },
+            actions: ["create_missing_note", "retarget_link"],
+          });
+        }
+        break;
+
+      case "dangling_target_heading":
+        // Similar to dangling_target, but for headings
+        todos.push({
+          type: "dangling_target_heading",
+          id: `dangling_target_heading_${finding.evidence?.file}_${finding.evidence?.sectionHeading}`,
+          description: finding.message,
+          priority: finding.severity === "warn" ? "medium" : "low",
+          targetFile: finding.evidence?.file || "",
+          targetHeading: finding.evidence?.sectionHeading || null,
+          actions: ["create_missing_heading", "retarget_to_existing_heading"],
+        });
+        break;
+
+      case "only_candidates":
+        // Find all candidate edges in section
+        const candidateEdges = allEdges.filter(
+          (e) => e.scope === "candidate" && 
+                 ("sectionHeading" in e.source 
+                   ? e.source.sectionHeading === context.heading 
+                   : false)
+        );
+        if (candidateEdges.length > 0) {
+          todos.push({
+            type: "only_candidates",
+            id: `only_candidates_${context.file}_${context.heading}`,
+            description: finding.message,
+            priority: "medium",
+            candidateEdges: candidateEdges.map((e) => ({
+              rawEdgeType: e.rawEdgeType,
+              from: "sectionHeading" in e.source
+                ? { file: e.source.file, heading: e.source.sectionHeading }
+                : { file: e.source.file, heading: null },
+              to: e.target,
+            })),
+            actions: ["promote_all_candidates", "create_explicit_edges"],
+          });
+        }
+        break;
+
+      case "missing_edges":
+        todos.push({
+          type: "missing_edges",
+          id: `missing_edges_${context.file}_${context.heading}`,
+          description: finding.message,
+          priority: "medium",
+          section: {
+            file: context.file,
+            heading: context.heading,
+          },
+          actions: ["add_edges_to_section"],
+        });
+        break;
+
+      case "no_causal_roles":
+        // Find edges without causal roles
+        const nonCausalEdges = allEdges.filter(
+          (e) => e.scope === "section" &&
+                 ("sectionHeading" in e.source
+                   ? e.source.sectionHeading === context.heading
+                   : false)
+        );
+        todos.push({
+          type: "no_causal_roles",
+          id: `no_causal_roles_${context.file}_${context.heading}`,
+          description: finding.message,
+          priority: "medium",
+          edges: nonCausalEdges.map((e) => ({
+            rawEdgeType: e.rawEdgeType,
+            from: "sectionHeading" in e.source
+              ? { file: e.source.file, heading: e.source.sectionHeading }
+              : { file: e.source.file, heading: null },
+            to: e.target,
+            currentRole: null, // Would need to resolve via chain_roles
+            suggestedRoles: ["causal", "influences", "enables_constraints"],
+          })),
+          actions: ["change_edge_type"],
+        });
+        break;
+
+      case "one_sided_connectivity":
+        // Informational only
+        todos.push({
+          type: "one_sided_connectivity",
+          id: `one_sided_connectivity_${context.file}_${context.heading}`,
+          description: finding.message,
+          priority: "low",
+          section: {
+            file: context.file,
+            heading: context.heading,
+          },
+          actions: [], // No actions, informational only
+        });
+        break;
+    }
+  }
+
+  return todos;
+}
+```
+
+### 2. Erweitere Todo-Types
+
+Füge neue Todo-Types zu `types.ts` hinzu:
+
+```typescript
+export type TodoType =
+  | "missing_slot"
+  | "missing_link"
+  | "weak_roles"
+  | "candidate_cleanup"
+  | "create_candidates_zone"
+  | "create_note_links_zone"
+  | "dangling_target"           // NEU
+  | "dangling_target_heading"    // NEU
+  | "only_candidates"            // NEU
+  | "missing_edges"              // NEU
+  | "no_causal_roles"            // NEU
+  | "one_sided_connectivity";     // NEU
+
+export interface DanglingTargetTodo extends WorkbenchTodo {
+  type: "dangling_target";
+  targetFile: string;
+  targetHeading: string | null;
+  sourceEdge: {
+    file: string;
+    heading: string | null;
+  };
+  actions: Array<"create_missing_note" | "retarget_link">;
+}
+
+export interface DanglingTargetHeadingTodo extends WorkbenchTodo {
+  type: "dangling_target_heading";
+  targetFile: string;
+  targetHeading: string | null;
+  actions: Array<"create_missing_heading" | "retarget_to_existing_heading">;
+}
+
+export interface OnlyCandidatesTodo extends WorkbenchTodo {
+  type: "only_candidates";
+  candidateEdges: Array<{
+    rawEdgeType: string;
+    from: { file: string; heading: string | null };
+    to: { file: string; heading: string | null };
+  }>;
+  actions: Array<"promote_all_candidates" | "create_explicit_edges">;
+}
+
+export interface MissingEdgesTodo extends WorkbenchTodo {
+  type: "missing_edges";
+  section: {
+    file: string;
+    heading: string | null;
+  };
+  actions: Array<"add_edges_to_section">;
+}
+
+export interface NoCausalRolesTodo extends WorkbenchTodo {
+  type: "no_causal_roles";
+  edges: Array<{
+    rawEdgeType: string;
+    from: { file: string; heading: string | null };
+    to: { file: string; heading: string | null };
+    currentRole: string | null;
+    suggestedRoles: string[];
+  }>;
+  actions: Array<"change_edge_type">;
+}
+
+export interface OneSidedConnectivityTodo extends WorkbenchTodo {
+  type: "one_sided_connectivity";
+  section: {
+    file: string;
+    heading: string | null;
+  };
+  actions: []; // Informational only
+}
+```
+
+### 3. Integriere Findings in Workbench Builder
+
+Erweitere `workbenchBuilder.ts`:
+
+```typescript
+export async function buildWorkbenchModel(
+  app: App,
+  report: ChainInspectorReport,
+  chainTemplates: ChainTemplatesConfig | null,
+  chainRoles: ChainRolesConfig | null,
+  edgeVocabulary: EdgeVocabulary | null,
+  allEdges: IndexedEdge[]
+): Promise<WorkbenchModel> {
+  const matches: WorkbenchMatch[] = [];
+  const globalTodos: WorkbenchTodoUnion[] = []; // NEU: Global todos from findings
+
+  // ... existing template match processing ...
+
+  // NEU: Generate todos from findings
+  if (report.findings && report.findings.length > 0) {
+    const findingsTodos = generateFindingsTodos(
+      report.findings,
+      allEdges,
+      report.context
+    );
+    globalTodos.push(...findingsTodos);
+  }
+
+  return {
+    context: report.context,
+    matches,
+    globalTodos, // NEU: Add global todos
+    timestamp: Date.now(),
+  };
+}
+```
+
+### 4. Erweitere WorkbenchModel Interface
+
+```typescript
+export interface WorkbenchModel {
+  context: {
+    file: string;
+    heading: string | null;
+    zoneKind: string;
+  };
+  matches: WorkbenchMatch[];
+  globalTodos?: WorkbenchTodoUnion[]; // NEU: Todos from findings (not template-based)
+  timestamp: number;
+}
+```
+
+### 5. UI-Integration
+
+Erweitere `ChainWorkbenchModal.ts`:
+
+```typescript
+// Show global todos (from findings) separately
+if (model.globalTodos && model.globalTodos.length > 0) {
+  // Render "Section-Level Issues" section
+  // Show findings-based todos before template matches
+}
+```
+
+---
+
+## Vorteile
+
+1. **Nutzt getestete Heuristiken** - Findings aus 0.4.x werden verwendet
+2. **Vollständigere Analyse** - Nicht nur Template-basiert, sondern auch Section-Level
+3. **Konsistenz** - Chain Inspector und Workbench zeigen dieselben Probleme
+4. **Bessere UX** - User sieht alle Probleme auf einen Blick
+
+---
+
+## Implementierungsreihenfolge
+
+1. **Phase 1:** Todo-Types erweitern (`types.ts`)
+2. **Phase 2:** `generateFindingsTodos()` implementieren (`todoGenerator.ts`)
+3. **Phase 3:** `buildWorkbenchModel()` erweitern (`workbenchBuilder.ts`)
+4. **Phase 4:** UI erweitern (`ChainWorkbenchModal.ts`)
+5. **Phase 5:** Actions implementieren (z.B. `create_missing_note`, `retarget_link`)
+
+---
+
+## Offene Fragen
+
+1. **Priorität:** Sollen Findings-Todos höhere Priorität haben als Template-Todos?
+2. **Duplikate:** Wie vermeiden wir Duplikate zwischen Findings-Todos und Template-Todos?
+   - Beispiel: `dangling_target` könnte auch als `missing_link` Todo erscheinen
+3. **Filterung:** Sollen Findings-Todos gefiltert werden können (z.B. nur Errors)?
+4. **Actions:** Welche Actions sind für welche Findings sinnvoll?
+
+---
+
+**Letzte Aktualisierung:** 2025-01-XX  
+**Status:** Vorschlag für zukünftige Implementierung

docs/readme.md

@@ -106,6 +106,7 @@ Diese Dokumentation deckt alle Aspekte des **Mindnet Causal Assistant** Plugins
 ### Konzepte & Details
 
 - [02_causal_chain_retrieving.md](./02_causal_chain_retrieving.md) - Kausale Ketten-Retrieval
+- [02_concepts/03_chain_identification_and_matching.md](./02_concepts/03_chain_identification_and_matching.md) - **Chain-Identifikation und Template Matching** - Vollständige Erklärung des Prozesses, wie Chains identifiziert und gefüllt werden
 - [DANGLING_TARGET_CASES.md](./DANGLING_TARGET_CASES.md) - Dangling Target Findings
 - [06_Konfigurationsdateien_Referenz.md](./06_Konfigurationsdateien_Referenz.md) - Vollständige Referenz aller Config-Dateien
 - [07_Event_Handler_Commands.md](./07_Event_Handler_Commands.md) - Event Handler & Commands Referenz
@@ -114,6 +115,15 @@ Diese Dokumentation deckt alle Aspekte des **Mindnet Causal Assistant** Plugins
 
 - [00_Dokumentations_Index.md](./00_Dokumentations_Index.md) - Vollständige Übersicht aller Dokumentationen
 
+### Testing
+
+- [08_Testing_Chain_Workbench.md](./08_Testing_Chain_Workbench.md) - Anleitung zum Testen der Chain Workbench und Vault Triage Features (0.5.x)
+
+### Architektur & Analyse-Basis
+
+- [09_Workbench_Analysis_Basis.md](./09_Workbench_Analysis_Basis.md) - Analyse-Basis der Chain Workbench (0.5.x) und Abhängigkeiten zu Chain Inspector (0.4.x)
+- [10_Workbench_Findings_Integration.md](./10_Workbench_Findings_Integration.md) - Vorschlag zur Integration der Findings aus 0.4.x in die Workbench
+
 ### Legacy-Dokumentation
 
 - [readme.md](./readme.md) - MVP 1.0 Quickstart

src/commands/chainWorkbenchCommand.ts

@@ -0,0 +1,112 @@
+/**
+ * Command: Chain Workbench (Current Section)
+ */
+
+import { Notice } from "obsidian";
+import type { App, Editor } from "obsidian";
+import { resolveSectionContext } from "../analysis/sectionContext";
+import { inspectChains } from "../analysis/chainInspector";
+import type { ChainRolesConfig, ChainTemplatesConfig, DictionaryLoadResult } from "../dictionary/types";
+import type { MindnetSettings } from "../settings";
+import { buildWorkbenchModel } from "../workbench/workbenchBuilder";
+import { buildNoteIndex } from "../analysis/graphIndex";
+import { TFile } from "obsidian";
+import { VocabularyLoader } from "../vocab/VocabularyLoader";
+import { parseEdgeVocabulary } from "../vocab/parseEdgeVocabulary";
+import { Vocabulary } from "../vocab/Vocabulary";
+
+/**
+ * Execute chain workbench command.
+ */
+export async function executeChainWorkbench(
+  app: App,
+  editor: Editor,
+  filePath: string,
+  chainRoles: ChainRolesConfig | null,
+  chainTemplates: ChainTemplatesConfig | null,
+  templatesLoadResult: DictionaryLoadResult<ChainTemplatesConfig> | undefined,
+  settings: MindnetSettings,
+  pluginInstance: any
+): Promise<void> {
+  try {
+    // Resolve section context
+    const context = resolveSectionContext(editor, filePath);
+
+    // Build inspector options
+    const inspectorOptions = {
+      includeNoteLinks: true,
+      includeCandidates: settings.chainInspectorIncludeCandidates,
+      maxDepth: 3,
+      direction: "both" as const,
+      maxTemplateMatches: undefined, // No limit - we want ALL matches
+    };
+
+    // Load vocabulary
+    const vocabText = await VocabularyLoader.loadText(app, settings.edgeVocabularyPath);
+    const edgeVocabulary = parseEdgeVocabulary(vocabText);
+    const vocabulary = new Vocabulary(edgeVocabulary);
+
+    // Prepare templates source info
+    let templatesSourceInfo: { path: string; status: string; loadedAt: number | null; templateCount: number } | undefined;
+    if (templatesLoadResult) {
+      templatesSourceInfo = {
+        path: templatesLoadResult.resolvedPath,
+        status: templatesLoadResult.status,
+        loadedAt: templatesLoadResult.loadedAt,
+        templateCount: chainTemplates?.templates?.length || 0,
+      };
+    }
+
+    // Inspect chains
+    const report = await inspectChains(
+      app,
+      context,
+      inspectorOptions,
+      chainRoles,
+      settings.edgeVocabularyPath,
+      chainTemplates,
+      templatesSourceInfo,
+      settings.templateMatchingProfile
+    );
+
+    // Build all edges index for todo generation
+    // Get edges from current note (includes candidates)
+    const activeFile = app.vault.getAbstractFileByPath(filePath);
+    if (!activeFile || !(activeFile instanceof TFile)) {
+      throw new Error("Active file not found");
+    }
+
+    const { edges: allEdges } = await buildNoteIndex(app, activeFile);
+    
+    // Also add edges from neighbors (for relation equality checking)
+    // These are already in the report but we need them in IndexedEdge format
+    // For now, we'll use the current note edges and check candidates from there
+
+    // Build workbench model
+    const workbenchModel = await buildWorkbenchModel(
+      app,
+      report,
+      chainTemplates,
+      chainRoles,
+      edgeVocabulary,
+      allEdges
+    );
+
+    // Open workbench UI
+    const { ChainWorkbenchModal } = await import("../ui/ChainWorkbenchModal");
+    const modal = new ChainWorkbenchModal(
+      app,
+      workbenchModel,
+      settings,
+      chainRoles,
+      chainTemplates,
+      vocabulary,
+      pluginInstance
+    );
+    modal.open();
+  } catch (e) {
+    const msg = e instanceof Error ? e.message : String(e);
+    console.error("[Chain Workbench] Error:", e);
+    new Notice(`Failed to open chain workbench: ${msg}`);
+  }
+}

src/commands/vaultTriageScanCommand.ts

@@ -0,0 +1,50 @@
+/**
+ * Command: Scan Vault for Chain Gaps
+ */
+
+import { Notice } from "obsidian";
+import type { App } from "obsidian";
+import type { ChainRolesConfig, ChainTemplatesConfig, DictionaryLoadResult } from "../dictionary/types";
+import type { MindnetSettings } from "../settings";
+import { scanVaultForChainGaps, saveScanState, loadScanState, type ScanState, type ScanItem } from "../workbench/vaultTriageScan";
+import { VocabularyLoader } from "../vocab/VocabularyLoader";
+import { parseEdgeVocabulary } from "../vocab/parseEdgeVocabulary";
+
+/**
+ * Execute vault triage scan command.
+ */
+export async function executeVaultTriageScan(
+  app: App,
+  chainRoles: ChainRolesConfig | null,
+  chainTemplates: ChainTemplatesConfig | null,
+  templatesLoadResult: DictionaryLoadResult<ChainTemplatesConfig> | undefined,
+  settings: MindnetSettings,
+  pluginInstance: any
+): Promise<void> {
+  try {
+    // Load vocabulary
+    const vocabText = await VocabularyLoader.loadText(app, settings.edgeVocabularyPath);
+    const edgeVocabulary = parseEdgeVocabulary(vocabText);
+
+    // Check for existing scan state
+    const existingState = await loadScanState(app, pluginInstance);
+    const shouldResume = existingState && !existingState.completed;
+
+    // Open scan UI
+    const { VaultTriageScanModal } = await import("../ui/VaultTriageScanModal");
+    const modal = new VaultTriageScanModal(
+      app,
+      chainRoles,
+      chainTemplates,
+      edgeVocabulary,
+      settings,
+      pluginInstance,
+      existingState
+    );
+    modal.open();
+  } catch (e) {
+    const msg = e instanceof Error ? e.message : String(e);
+    console.error("[Vault Triage Scan] Error:", e);
+    new Notice(`Failed to start vault triage scan: ${msg}`);
+  }
+}

src/main.ts

@@ -587,6 +587,77 @@ export default class MindnetCausalAssistantPlugin extends Plugin {
       },
     });
 
+    this.addCommand({
+      id: "mindnet-chain-workbench",
+      name: "Mindnet: Chain Workbench (Current Section)",
+      editorCallback: async (editor) => {
+        try {
+          const activeFile = this.app.workspace.getActiveFile();
+          if (!activeFile) {
+            new Notice("No active file");
+            return;
+          }
+
+          if (activeFile.extension !== "md") {
+            new Notice("Active file is not a markdown file");
+            return;
+          }
+
+          // Ensure chain roles and templates are loaded
+          await this.ensureChainRolesLoaded();
+          const chainRoles = this.chainRoles.data;
+          await this.ensureChainTemplatesLoaded();
+          const chainTemplates = this.chainTemplates.data;
+          const templatesLoadResult = this.chainTemplates.result;
+
+          const { executeChainWorkbench } = await import("./commands/chainWorkbenchCommand");
+          await executeChainWorkbench(
+            this.app,
+            editor,
+            activeFile.path,
+            chainRoles,
+            chainTemplates,
+            templatesLoadResult || undefined,
+            this.settings,
+            this
+          );
+        } catch (e) {
+          const msg = e instanceof Error ? e.message : String(e);
+          new Notice(`Failed to open chain workbench: ${msg}`);
+          console.error(e);
+        }
+      },
+    });
+
+    this.addCommand({
+      id: "mindnet-scan-chain-gaps",
+      name: "Mindnet: Scan Vault for Chain Gaps",
+      callback: async () => {
+        try {
+          // Ensure chain roles and templates are loaded
+          await this.ensureChainRolesLoaded();
+          const chainRoles = this.chainRoles.data;
+          await this.ensureChainTemplatesLoaded();
+          const chainTemplates = this.chainTemplates.data;
+          const templatesLoadResult = this.chainTemplates.result;
+
+          const { executeVaultTriageScan } = await import("./commands/vaultTriageScanCommand");
+          await executeVaultTriageScan(
+            this.app,
+            chainRoles,
+            chainTemplates,
+            templatesLoadResult || undefined,
+            this.settings,
+            this
+          );
+        } catch (e) {
+          const msg = e instanceof Error ? e.message : String(e);
+          new Notice(`Failed to start vault triage scan: ${msg}`);
+          console.error(e);
+        }
+      },
+    });
+
     this.addCommand({
       id: "mindnet-build-semantic-mappings",
       name: "Mindnet: Build semantic mapping blocks (by section)",

src/tests/workbench/statusCalculator.test.ts

@@ -0,0 +1,324 @@
+/**
+ * Tests for status calculator.
+ */
+
+import { describe, it, expect } from "vitest";
+import {
+  calculateMatchStatus,
+  calculateSlotsStats,
+  hasWeakRoles,
+  getEffectiveRequiredLinks,
+} from "../../workbench/statusCalculator";
+import type { TemplateMatch } from "../../analysis/chainInspector";
+
+describe("calculateMatchStatus", () => {
+  it("should return 'complete' when all slots filled and all links satisfied", () => {
+    const match: TemplateMatch = {
+      templateName: "test_template",
+      score: 20,
+      slotAssignments: {
+        slot1: { nodeKey: "file1:", file: "file1.md", heading: null, noteType: "concept" },
+        slot2: { nodeKey: "file2:", file: "file2.md", heading: null, noteType: "concept" },
+      },
+      missingSlots: [],
+      satisfiedLinks: 2,
+      requiredLinks: 2,
+      slotsComplete: true,
+      linksComplete: true,
+      confidence: "confirmed",
+    };
+
+    const status = calculateMatchStatus(match, false);
+    expect(status).toBe("complete");
+  });
+
+  it("should return 'near_complete' when slots complete but 1 link missing", () => {
+    const match: TemplateMatch = {
+      templateName: "test_template",
+      score: 18,
+      slotAssignments: {
+        slot1: { nodeKey: "file1:", file: "file1.md", heading: null, noteType: "concept" },
+        slot2: { nodeKey: "file2:", file: "file2.md", heading: null, noteType: "concept" },
+      },
+      missingSlots: [],
+      satisfiedLinks: 1,
+      requiredLinks: 2,
+      slotsComplete: true,
+      linksComplete: false,
+      confidence: "plausible",
+    };
+
+    const status = calculateMatchStatus(match, false);
+    expect(status).toBe("near_complete");
+  });
+
+  it("should return 'near_complete' when 1 slot missing but all links satisfied", () => {
+    const match: TemplateMatch = {
+      templateName: "test_template",
+      score: 18,
+      slotAssignments: {
+        slot1: { nodeKey: "file1:", file: "file1.md", heading: null, noteType: "concept" },
+      },
+      missingSlots: ["slot2"],
+      satisfiedLinks: 1,
+      requiredLinks: 1,
+      slotsComplete: false,
+      linksComplete: true,
+      confidence: "plausible",
+    };
+
+    const status = calculateMatchStatus(match, false);
+    expect(status).toBe("near_complete");
+  });
+
+  it("should return 'weak' when hasWeakRoles is true", () => {
+    const match: TemplateMatch = {
+      templateName: "test_template",
+      score: 10,
+      slotAssignments: {
+        slot1: { nodeKey: "file1:", file: "file1.md", heading: null, noteType: "concept" },
+      },
+      missingSlots: ["slot2"],
+      satisfiedLinks: 0,
+      requiredLinks: 1,
+      slotsComplete: false,
+      linksComplete: false,
+      confidence: "weak",
+    };
+
+    const status = calculateMatchStatus(match, true);
+    expect(status).toBe("weak");
+  });
+
+  it("should return 'partial' for other cases", () => {
+    const match: TemplateMatch = {
+      templateName: "test_template",
+      score: 8,
+      slotAssignments: {
+        slot1: { nodeKey: "file1:", file: "file1.md", heading: null, noteType: "concept" },
+      },
+      missingSlots: ["slot2", "slot3"],
+      satisfiedLinks: 0,
+      requiredLinks: 2,
+      slotsComplete: false,
+      linksComplete: false,
+      confidence: "weak",
+    };
+
+    const status = calculateMatchStatus(match, false);
+    expect(status).toBe("partial");
+  });
+});
+
+describe("calculateSlotsStats", () => {
+  it("should calculate filled and total slots correctly", () => {
+    const match: TemplateMatch = {
+      templateName: "test_template",
+      score: 10,
+      slotAssignments: {
+        slot1: { nodeKey: "file1:", file: "file1.md", heading: null, noteType: "concept" },
+        slot2: { nodeKey: "file2:", file: "file2.md", heading: null, noteType: "concept" },
+      },
+      missingSlots: ["slot3"],
+      satisfiedLinks: 0,
+      requiredLinks: 0,
+      slotsComplete: false,
+      linksComplete: true,
+      confidence: "plausible",
+    };
+
+    const stats = calculateSlotsStats(match);
+    expect(stats.filled).toBe(2);
+    expect(stats.total).toBe(3);
+  });
+
+  it("should handle empty slots", () => {
+    const match: TemplateMatch = {
+      templateName: "test_template",
+      score: 0,
+      slotAssignments: {},
+      missingSlots: ["slot1", "slot2"],
+      satisfiedLinks: 0,
+      requiredLinks: 0,
+      slotsComplete: false,
+      linksComplete: true,
+      confidence: "weak",
+    };
+
+    const stats = calculateSlotsStats(match);
+    expect(stats.filled).toBe(0);
+    expect(stats.total).toBe(2);
+  });
+});
+
+describe("hasWeakRoles", () => {
+  it("should return false when no roleEvidence", () => {
+    const match: TemplateMatch = {
+      templateName: "test_template",
+      score: 10,
+      slotAssignments: {},
+      missingSlots: [],
+      satisfiedLinks: 0,
+      requiredLinks: 0,
+      slotsComplete: true,
+      linksComplete: true,
+      confidence: "confirmed",
+    };
+
+    expect(hasWeakRoles(match)).toBe(false);
+  });
+
+  it("should return false when causal roles present", () => {
+    const match: TemplateMatch = {
+      templateName: "test_template",
+      score: 10,
+      slotAssignments: {},
+      missingSlots: [],
+      satisfiedLinks: 1,
+      requiredLinks: 1,
+      slotsComplete: true,
+      linksComplete: true,
+      confidence: "confirmed",
+      roleEvidence: [
+        {
+          from: "file1:",
+          to: "file2:",
+          edgeRole: "causal",
+          rawEdgeType: "caused_by",
+        },
+      ],
+    };
+
+    expect(hasWeakRoles(match)).toBe(false);
+  });
+
+  it("should return true when only structural/temporal roles", () => {
+    const match: TemplateMatch = {
+      templateName: "test_template",
+      score: 10,
+      slotAssignments: {},
+      missingSlots: [],
+      satisfiedLinks: 1,
+      requiredLinks: 1,
+      slotsComplete: true,
+      linksComplete: true,
+      confidence: "weak",
+      roleEvidence: [
+        {
+          from: "file1:",
+          to: "file2:",
+          edgeRole: "structural",
+          rawEdgeType: "part_of",
+        },
+        {
+          from: "file2:",
+          to: "file3:",
+          edgeRole: "temporal",
+          rawEdgeType: "followed_by",
+        },
+      ],
+    };
+
+    expect(hasWeakRoles(match)).toBe(true);
+  });
+
+  it("should return false when mixed roles (causal + structural)", () => {
+    const match: TemplateMatch = {
+      templateName: "test_template",
+      score: 10,
+      slotAssignments: {},
+      missingSlots: [],
+      satisfiedLinks: 2,
+      requiredLinks: 2,
+      slotsComplete: true,
+      linksComplete: true,
+      confidence: "confirmed",
+      roleEvidence: [
+        {
+          from: "file1:",
+          to: "file2:",
+          edgeRole: "causal",
+          rawEdgeType: "caused_by",
+        },
+        {
+          from: "file2:",
+          to: "file3:",
+          edgeRole: "structural",
+          rawEdgeType: "part_of",
+        },
+      ],
+    };
+
+    expect(hasWeakRoles(match)).toBe(false);
+  });
+});
+
+describe("getEffectiveRequiredLinks", () => {
+  it("should prioritize template.matching.required_links", () => {
+    const match: TemplateMatch = {
+      templateName: "test_template",
+      score: 10,
+      slotAssignments: {},
+      missingSlots: [],
+      satisfiedLinks: 0,
+      requiredLinks: 0,
+      slotsComplete: true,
+      linksComplete: true,
+      confidence: "confirmed",
+    };
+
+    const result = getEffectiveRequiredLinks(match, false, true, false);
+    expect(result).toBe(true);
+  });
+
+  it("should fall back to profile.required_links when template not set", () => {
+    const match: TemplateMatch = {
+      templateName: "test_template",
+      score: 10,
+      slotAssignments: {},
+      missingSlots: [],
+      satisfiedLinks: 0,
+      requiredLinks: 0,
+      slotsComplete: true,
+      linksComplete: true,
+      confidence: "confirmed",
+    };
+
+    const result = getEffectiveRequiredLinks(match, true, undefined, false);
+    expect(result).toBe(true);
+  });
+
+  it("should fall back to defaults.matching.required_links when profile not set", () => {
+    const match: TemplateMatch = {
+      templateName: "test_template",
+      score: 10,
+      slotAssignments: {},
+      missingSlots: [],
+      satisfiedLinks: 0,
+      requiredLinks: 0,
+      slotsComplete: true,
+      linksComplete: true,
+      confidence: "confirmed",
+    };
+
+    const result = getEffectiveRequiredLinks(match, undefined, undefined, true);
+    expect(result).toBe(true);
+  });
+
+  it("should return false as fallback when nothing set", () => {
+    const match: TemplateMatch = {
+      templateName: "test_template",
+      score: 10,
+      slotAssignments: {},
+      missingSlots: [],
+      satisfiedLinks: 0,
+      requiredLinks: 0,
+      slotsComplete: true,
+      linksComplete: true,
+      confidence: "confirmed",
+    };
+
+    const result = getEffectiveRequiredLinks(match, undefined, undefined, undefined);
+    expect(result).toBe(false);
+  });
+});

src/tests/workbench/todoGenerator.test.ts

@@ -0,0 +1,401 @@
+/**
+ * Tests for todo generator.
+ */
+
+import { describe, it, expect } from "vitest";
+import { generateTodos } from "../../workbench/todoGenerator";
+import type { TemplateMatch } from "../../analysis/chainInspector";
+import type { ChainTemplate } from "../../dictionary/types";
+import type { ChainRolesConfig } from "../../dictionary/types";
+import type { IndexedEdge } from "../../analysis/graphIndex";
+import type { EdgeVocabulary } from "../../vocab/types";
+
+// Mock App
+const mockApp = {
+  vault: {},
+} as any;
+
+// Mock Edge Vocabulary
+const mockEdgeVocabulary: EdgeVocabulary = {
+  byCanonical: new Map([
+    ["caused_by", { canonical: "caused_by", aliases: [], description: "" }],
+    ["impacts", { canonical: "impacts", aliases: [], description: "" }],
+  ]),
+  aliasToCanonical: new Map(),
+};
+
+// Mock Chain Roles
+const mockChainRoles: ChainRolesConfig = {
+  roles: {
+    causal: {
+      edge_types: ["caused_by", "resulted_in"],
+    },
+    influences: {
+      edge_types: ["impacts", "impacted_by"],
+    },
+  },
+};
+
+describe("generateTodos", () => {
+  it("should generate missing_slot todo for missing slots", async () => {
+    const match: TemplateMatch = {
+      templateName: "test_template",
+      score: 10,
+      slotAssignments: {
+        slot1: { nodeKey: "file1:", file: "file1.md", heading: null, noteType: "concept" },
+      },
+      missingSlots: ["slot2"],
+      satisfiedLinks: 0,
+      requiredLinks: 0,
+      slotsComplete: false,
+      linksComplete: true,
+      confidence: "plausible",
+    };
+
+    const template: ChainTemplate = {
+      name: "test_template",
+      slots: [
+        { id: "slot1", allowed_node_types: ["concept"] },
+        { id: "slot2", allowed_node_types: ["decision"] },
+      ],
+      links: [],
+    };
+
+    const todos = await generateTodos(
+      mockApp,
+      match,
+      template,
+      null,
+      null,
+      [],
+      [],
+      [],
+      { file: "test.md", heading: null }
+    );
+
+    expect(todos.length).toBeGreaterThan(0);
+    const missingSlotTodo = todos.find((t) => t.type === "missing_slot");
+    expect(missingSlotTodo).toBeDefined();
+    expect(missingSlotTodo?.type).toBe("missing_slot");
+    if (missingSlotTodo && missingSlotTodo.type === "missing_slot") {
+      expect(missingSlotTodo.slotId).toBe("slot2");
+      expect(missingSlotTodo.allowedNodeTypes).toEqual(["decision"]);
+    }
+  });
+
+  it("should generate missing_link todo when slots filled but link missing", async () => {
+    const match: TemplateMatch = {
+      templateName: "test_template",
+      score: 10,
+      slotAssignments: {
+        slot1: { nodeKey: "file1:", file: "file1.md", heading: null, noteType: "concept" },
+        slot2: { nodeKey: "file2:", file: "file2.md", heading: null, noteType: "decision" },
+      },
+      missingSlots: [],
+      satisfiedLinks: 0,
+      requiredLinks: 1,
+      slotsComplete: true,
+      linksComplete: false,
+      confidence: "plausible",
+    };
+
+    const template: ChainTemplate = {
+      name: "test_template",
+      slots: [
+        { id: "slot1", allowed_node_types: ["concept"] },
+        { id: "slot2", allowed_node_types: ["decision"] },
+      ],
+      links: [
+        {
+          from: "slot1",
+          to: "slot2",
+          allowed_edge_roles: ["causal"],
+        },
+      ],
+    };
+
+    const todos = await generateTodos(
+      mockApp,
+      match,
+      template,
+      mockChainRoles,
+      mockEdgeVocabulary,
+      [],
+      [],
+      [],
+      { file: "test.md", heading: null }
+    );
+
+    expect(todos.length).toBeGreaterThan(0);
+    const missingLinkTodo = todos.find((t) => t.type === "missing_link");
+    expect(missingLinkTodo).toBeDefined();
+    expect(missingLinkTodo?.type).toBe("missing_link");
+    if (missingLinkTodo && missingLinkTodo.type === "missing_link") {
+      expect(missingLinkTodo.fromSlotId).toBe("slot1");
+      expect(missingLinkTodo.toSlotId).toBe("slot2");
+      expect(missingLinkTodo.suggestedEdgeTypes).toContain("caused_by");
+      expect(missingLinkTodo.suggestedEdgeTypes).toContain("resulted_in");
+    }
+  });
+
+  it("should not generate missing_link todo when link exists", async () => {
+    const match: TemplateMatch = {
+      templateName: "test_template",
+      score: 10,
+      slotAssignments: {
+        slot1: { nodeKey: "file1:", file: "file1.md", heading: null, noteType: "concept" },
+        slot2: { nodeKey: "file2:", file: "file2.md", heading: null, noteType: "decision" },
+      },
+      missingSlots: [],
+      satisfiedLinks: 1,
+      requiredLinks: 1,
+      slotsComplete: true,
+      linksComplete: true,
+      confidence: "confirmed",
+      roleEvidence: [
+        {
+          // roleEvidence uses nodeKey format: "file:heading"
+          from: "file1.md:",
+          to: "file2.md:",
+          edgeRole: "causal",
+          rawEdgeType: "caused_by",
+        },
+      ],
+    };
+
+    const template: ChainTemplate = {
+      name: "test_template",
+      slots: [
+        { id: "slot1", allowed_node_types: ["concept"] },
+        { id: "slot2", allowed_node_types: ["decision"] },
+      ],
+      links: [
+        {
+          from: "slot1",
+          to: "slot2",
+          allowed_edge_roles: ["causal"],
+        },
+      ],
+    };
+
+    const todos = await generateTodos(
+      mockApp,
+      match,
+      template,
+      mockChainRoles,
+      mockEdgeVocabulary,
+      [],
+      [],
+      [],
+      { file: "test.md", heading: null }
+    );
+
+    const missingLinkTodo = todos.find((t) => t.type === "missing_link");
+    expect(missingLinkTodo).toBeUndefined();
+  });
+
+  it("should generate weak_roles todo when only structural/temporal roles", async () => {
+    const match: TemplateMatch = {
+      templateName: "test_template",
+      score: 10,
+      slotAssignments: {
+        slot1: { nodeKey: "file1:", file: "file1.md", heading: null, noteType: "concept" },
+        slot2: { nodeKey: "file2:", file: "file2.md", heading: null, noteType: "concept" },
+      },
+      missingSlots: [],
+      satisfiedLinks: 2,
+      requiredLinks: 2,
+      slotsComplete: true,
+      linksComplete: true,
+      confidence: "weak",
+      roleEvidence: [
+        {
+          from: "file1:",
+          to: "file2:",
+          edgeRole: "structural",
+          rawEdgeType: "part_of",
+        },
+        {
+          from: "file2:",
+          to: "file3:",
+          edgeRole: "temporal",
+          rawEdgeType: "followed_by",
+        },
+      ],
+    };
+
+    const template: ChainTemplate = {
+      name: "test_template",
+      slots: [
+        { id: "slot1", allowed_node_types: ["concept"] },
+        { id: "slot2", allowed_node_types: ["concept"] },
+      ],
+      links: [],
+    };
+
+    const allEdges: IndexedEdge[] = [
+      {
+        rawEdgeType: "part_of",
+        source: { file: "file1.md", sectionHeading: null },
+        target: { file: "file2.md", heading: null },
+        scope: "section",
+        evidence: { file: "test.md", sectionHeading: null },
+      },
+      {
+        rawEdgeType: "followed_by",
+        source: { file: "file2.md", sectionHeading: null },
+        target: { file: "file3.md", heading: null },
+        scope: "section",
+        evidence: { file: "test.md", sectionHeading: null },
+      },
+    ];
+
+    const todos = await generateTodos(
+      mockApp,
+      match,
+      template,
+      mockChainRoles,
+      mockEdgeVocabulary,
+      allEdges,
+      [],
+      [],
+      { file: "test.md", heading: null }
+    );
+
+    const weakRolesTodo = todos.find((t) => t.type === "weak_roles");
+    expect(weakRolesTodo).toBeDefined();
+    expect(weakRolesTodo?.type).toBe("weak_roles");
+    if (weakRolesTodo && weakRolesTodo.type === "weak_roles") {
+      expect(weakRolesTodo.edges.length).toBe(2);
+    }
+  });
+
+  it("should generate candidate_cleanup todo when candidate matches missing link", async () => {
+    const match: TemplateMatch = {
+      templateName: "test_template",
+      score: 10,
+      slotAssignments: {
+        slot1: { nodeKey: "file1:", file: "file1.md", heading: null, noteType: "concept" },
+        slot2: { nodeKey: "file2:", file: "file2.md", heading: null, noteType: "decision" },
+      },
+      missingSlots: [],
+      satisfiedLinks: 0,
+      requiredLinks: 1,
+      slotsComplete: true,
+      linksComplete: false,
+      confidence: "plausible",
+    };
+
+    const template: ChainTemplate = {
+      name: "test_template",
+      slots: [
+        { id: "slot1", allowed_node_types: ["concept"] },
+        { id: "slot2", allowed_node_types: ["decision"] },
+      ],
+      links: [
+        {
+          from: "slot1",
+          to: "slot2",
+          allowed_edge_roles: ["causal"],
+        },
+      ],
+    };
+
+    const candidateEdges: IndexedEdge[] = [
+      {
+        rawEdgeType: "caused_by",
+        source: { file: "file1.md", sectionHeading: null },
+        target: { file: "file2.md", heading: null },
+        scope: "candidate",
+        evidence: { file: "test.md", sectionHeading: "Kandidaten", lineRange: { start: 5, end: 7 } },
+      },
+    ];
+
+    const todos = await generateTodos(
+      mockApp,
+      match,
+      template,
+      mockChainRoles,
+      mockEdgeVocabulary,
+      [],
+      candidateEdges,
+      [],
+      { file: "test.md", heading: null }
+    );
+
+    const candidateCleanupTodo = todos.find((t) => t.type === "candidate_cleanup");
+    expect(candidateCleanupTodo).toBeDefined();
+    expect(candidateCleanupTodo?.type).toBe("candidate_cleanup");
+    if (candidateCleanupTodo && candidateCleanupTodo.type === "candidate_cleanup") {
+      expect(candidateCleanupTodo.candidateEdge.rawEdgeType).toBe("caused_by");
+      expect(candidateCleanupTodo.neededFor.matchName).toBe("test_template");
+    }
+  });
+
+  it("should not generate candidate_cleanup when confirmed edge exists", async () => {
+    const match: TemplateMatch = {
+      templateName: "test_template",
+      score: 10,
+      slotAssignments: {
+        slot1: { nodeKey: "file1:", file: "file1.md", heading: null, noteType: "concept" },
+        slot2: { nodeKey: "file2:", file: "file2.md", heading: null, noteType: "decision" },
+      },
+      missingSlots: [],
+      satisfiedLinks: 0,
+      requiredLinks: 1,
+      slotsComplete: true,
+      linksComplete: false,
+      confidence: "plausible",
+    };
+
+    const template: ChainTemplate = {
+      name: "test_template",
+      slots: [
+        { id: "slot1", allowed_node_types: ["concept"] },
+        { id: "slot2", allowed_node_types: ["decision"] },
+      ],
+      links: [
+        {
+          from: "slot1",
+          to: "slot2",
+          allowed_edge_roles: ["causal"],
+        },
+      ],
+    };
+
+    const candidateEdges: IndexedEdge[] = [
+      {
+        rawEdgeType: "caused_by",
+        source: { file: "file1.md", sectionHeading: null },
+        target: { file: "file2.md", heading: null },
+        scope: "candidate",
+        evidence: { file: "test.md", sectionHeading: "Kandidaten" },
+      },
+    ];
+
+    const confirmedEdges: IndexedEdge[] = [
+      {
+        rawEdgeType: "caused_by",
+        source: { file: "file1.md", sectionHeading: null },
+        target: { file: "file2.md", heading: null },
+        scope: "section",
+        evidence: { file: "test.md", sectionHeading: "My Section" },
+      },
+    ];
+
+    const todos = await generateTodos(
+      mockApp,
+      match,
+      template,
+      mockChainRoles,
+      mockEdgeVocabulary,
+      [],
+      candidateEdges,
+      confirmedEdges,
+      { file: "test.md", heading: null }
+    );
+
+    const candidateCleanupTodo = todos.find((t) => t.type === "candidate_cleanup");
+    expect(candidateCleanupTodo).toBeUndefined();
+  });
+});

src/tests/workbench/zoneDetector.test.ts

@@ -0,0 +1,210 @@
+/**
+ * Tests for zone detector.
+ */
+
+import { describe, it, expect, beforeEach } from "vitest";
+import { detectZone, findSection } from "../../workbench/zoneDetector";
+import type { App, TFile } from "obsidian";
+
+// Mock App
+function createMockApp(content: string): { app: App; file: TFile } {
+  const file = {
+    path: "test.md",
+    name: "test.md",
+    extension: "md",
+    basename: "test",
+    stat: { size: 0, ctime: 0, mtime: 0 },
+    vault: {} as any,
+    parent: null,
+  } as TFile;
+
+  const app = {
+    vault: {
+      read: async (f: TFile) => {
+        if (f.path === file.path) {
+          return content;
+        }
+        throw new Error("File not found");
+      },
+    },
+  } as unknown as App;
+
+  return { app, file };
+}
+
+describe("detectZone", () => {
+  it("should detect existing candidates zone", async () => {
+    const content = `# Test Note
+
+Some content.
+
+## Kandidaten
+
+> [!abstract]
+> [!edge] caused_by
+> [[Target Note]]
+
+## Other Section
+
+More content.
+`;
+
+    const { app, file } = createMockApp(content);
+    const zone = await detectZone(app, file, "candidates");
+
+    expect(zone.exists).toBe(true);
+    expect(zone.heading).toBe("## Kandidaten");
+    expect(zone.startLine).toBeGreaterThanOrEqual(0);
+    expect(zone.endLine).toBeGreaterThan(zone.startLine);
+    expect(zone.content).toContain("Kandidaten");
+    expect(zone.content).toContain("caused_by");
+  });
+
+  it("should detect existing note_links zone", async () => {
+    const content = `# Test Note
+
+Some content.
+
+## Note-Verbindungen
+
+> [!abstract]
+> [!edge] impacts
+> [[Other Note]]
+
+## Other Section
+
+More content.
+`;
+
+    const { app, file } = createMockApp(content);
+    const zone = await detectZone(app, file, "note_links");
+
+    expect(zone.exists).toBe(true);
+    expect(zone.heading).toBe("## Note-Verbindungen");
+    expect(zone.content).toContain("Note-Verbindungen");
+  });
+
+  it("should return exists=false when zone not found", async () => {
+    const content = `# Test Note
+
+Some content.
+
+## Other Section
+
+More content.
+`;
+
+    const { app, file } = createMockApp(content);
+    const zone = await detectZone(app, file, "candidates");
+
+    expect(zone.exists).toBe(false);
+    expect(zone.startLine).toBe(-1);
+  });
+
+  it("should handle zone at end of file", async () => {
+    const content = `# Test Note
+
+Some content.
+
+## Kandidaten
+
+> [!abstract]
+> [!edge] caused_by
+> [[Target Note]]
+`;
+
+    const { app, file } = createMockApp(content);
+    const zone = await detectZone(app, file, "candidates");
+
+    expect(zone.exists).toBe(true);
+    expect(zone.endLine).toBeGreaterThan(zone.startLine);
+  });
+});
+
+describe("findSection", () => {
+  it("should find section by heading", async () => {
+    const content = `# Test Note
+
+Some content.
+
+## My Section
+
+Section content here.
+
+## Other Section
+
+More content.
+`;
+
+    const { app, file } = createMockApp(content);
+    const section = await findSection(app, file, "My Section");
+
+    expect(section).not.toBeNull();
+    expect(section?.exists).toBe(true);
+    expect(section?.heading).toBe("My Section");
+    expect(section?.content).toContain("Section content here");
+  });
+
+  it("should find root section (null heading)", async () => {
+    const content = `Root content before first heading.
+
+## First Heading
+
+Content after heading.
+`;
+
+    const { app, file } = createMockApp(content);
+    const section = await findSection(app, file, null);
+
+    expect(section).not.toBeNull();
+    expect(section?.exists).toBe(true);
+    expect(section?.heading).toBe("");
+    expect(section?.content).toContain("Root content");
+    expect(section?.content).not.toContain("First Heading");
+  });
+
+  it("should return null when section not found", async () => {
+    const content = `# Test Note
+
+Some content.
+
+## Other Section
+
+More content.
+`;
+
+    const { app, file } = createMockApp(content);
+    const section = await findSection(app, file, "Non-existent Section");
+
+    expect(section).toBeNull();
+  });
+
+  it("should handle section boundaries correctly", async () => {
+    const content = `# Level 1
+
+Content 1.
+
+## Level 2
+
+Content 2.
+
+### Level 3
+
+Content 3.
+
+## Another Level 2
+
+Content 4.
+`;
+
+    const { app, file } = createMockApp(content);
+    const section = await findSection(app, file, "Level 2");
+
+    expect(section).not.toBeNull();
+    expect(section?.content).toContain("Content 2");
+    // Level 3 is a sub-section of Level 2, so it should be included
+    expect(section?.content).toContain("Content 3");
+    expect(section?.content).not.toContain("Another Level 2");
+    expect(section?.content).not.toContain("Content 4");
+  });
+});

src/ui/ChainWorkbenchModal.ts

@@ -0,0 +1,678 @@
+/**
+ * Chain Workbench Modal - UI for chain workbench.
+ */
+
+import { Modal, Setting, Notice } from "obsidian";
+import type { App } from "obsidian";
+import type { WorkbenchModel, WorkbenchMatch, WorkbenchTodoUnion } from "../workbench/types";
+import type { MindnetSettings } from "../settings";
+import type { ChainRolesConfig, ChainTemplatesConfig } from "../dictionary/types";
+import type { Vocabulary } from "../vocab/Vocabulary";
+
+export class ChainWorkbenchModal extends Modal {
+  private model: WorkbenchModel;
+  private settings: MindnetSettings;
+  private chainRoles: ChainRolesConfig | null;
+  private chainTemplates: ChainTemplatesConfig | null;
+  private vocabulary: Vocabulary;
+  private pluginInstance: any;
+
+  private selectedMatch: WorkbenchMatch | null = null;
+  private filterStatus: string | null = null;
+  private searchQuery: string = "";
+
+  constructor(
+    app: App,
+    model: WorkbenchModel,
+    settings: MindnetSettings,
+    chainRoles: ChainRolesConfig | null,
+    chainTemplates: ChainTemplatesConfig | null,
+    vocabulary: Vocabulary,
+    pluginInstance: any
+  ) {
+    super(app);
+    this.model = model;
+    this.settings = settings;
+    this.chainRoles = chainRoles;
+    this.chainTemplates = chainTemplates;
+    this.vocabulary = vocabulary;
+    this.pluginInstance = pluginInstance;
+  }
+
+  onOpen(): void {
+    const { contentEl } = this;
+    contentEl.empty();
+
+    // Header
+    contentEl.createEl("h2", { text: "Chain Workbench" });
+    contentEl.createEl("p", {
+      text: `Context: ${this.model.context.file}${this.model.context.heading ? `#${this.model.context.heading}` : ""}`,
+    });
+
+    // Filters
+    const filterContainer = contentEl.createDiv({ cls: "workbench-filters" });
+    filterContainer.createEl("label", { text: "Filter by Status:" });
+    const statusSelect = filterContainer.createEl("select");
+    statusSelect.createEl("option", { text: "All", value: "" });
+    statusSelect.createEl("option", { text: "Complete", value: "complete" });
+    statusSelect.createEl("option", { text: "Near Complete", value: "near_complete" });
+    statusSelect.createEl("option", { text: "Partial", value: "partial" });
+    statusSelect.createEl("option", { text: "Weak", value: "weak" });
+    statusSelect.addEventListener("change", (e) => {
+      const target = e.target as HTMLSelectElement;
+      this.filterStatus = target.value || null;
+      this.render();
+    });
+
+    filterContainer.createEl("label", { text: "Search:" });
+    const searchInput = filterContainer.createEl("input", { type: "text", placeholder: "Template name..." });
+    searchInput.addEventListener("input", (e) => {
+      const target = e.target as HTMLInputElement;
+      this.searchQuery = target.value.toLowerCase();
+      this.render();
+    });
+
+    // Main container: list + details
+    const mainContainer = contentEl.createDiv({ cls: "workbench-main" });
+
+    // Left: Match list
+    const listContainer = mainContainer.createDiv({ cls: "workbench-list" });
+    listContainer.createEl("h3", { text: "Template Matches" });
+
+    // Right: Details
+    const detailsContainer = mainContainer.createDiv({ cls: "workbench-details" });
+    detailsContainer.createEl("h3", { text: "Details" });
+
+    // Global todos section (if any)
+    if (this.model.globalTodos && this.model.globalTodos.length > 0) {
+      const globalTodosSection = contentEl.createDiv({ cls: "workbench-global-todos" });
+      globalTodosSection.createEl("h3", { text: "Section-Level Issues" });
+      globalTodosSection.createEl("p", {
+        text: `Found ${this.model.globalTodos.length} issue(s) from Chain Inspector findings`,
+      });
+    }
+
+    this.render();
+  }
+
+  private render(): void {
+    const { contentEl } = this;
+
+    // Filter matches
+    let filteredMatches = this.model.matches;
+    if (this.filterStatus) {
+      filteredMatches = filteredMatches.filter((m) => m.status === this.filterStatus);
+    }
+    if (this.searchQuery) {
+      filteredMatches = filteredMatches.filter((m) =>
+        m.templateName.toLowerCase().includes(this.searchQuery)
+      );
+    }
+
+    // Sort: near_complete first (default), then by score descending
+    filteredMatches.sort((a, b) => {
+      if (a.status === "near_complete" && b.status !== "near_complete") return -1;
+      if (a.status !== "near_complete" && b.status === "near_complete") return 1;
+      return b.score - a.score;
+    });
+
+    // Render list
+    const listContainer = contentEl.querySelector(".workbench-list");
+    if (listContainer) {
+      listContainer.empty();
+      listContainer.createEl("h3", { text: `Template Matches (${filteredMatches.length})` });
+
+      for (const match of filteredMatches) {
+        const matchEl = listContainer.createDiv({ cls: "workbench-match-item" });
+        if (this.selectedMatch === match) {
+          matchEl.addClass("selected");
+        }
+
+        const statusIcon = this.getStatusIcon(match.status);
+        matchEl.createEl("div", {
+          cls: "match-header",
+          text: `${statusIcon} ${match.templateName}`,
+        });
+
+        matchEl.createEl("div", {
+          cls: "match-stats",
+          text: `Slots: ${match.slotsFilled}/${match.slotsTotal} | Links: ${match.satisfiedLinks}/${match.requiredLinks} | Score: ${match.score}`,
+        });
+
+        matchEl.createEl("div", {
+          cls: "match-todos-count",
+          text: `${match.todos.length} todo(s)`,
+        });
+
+        matchEl.addEventListener("click", () => {
+          this.selectedMatch = match;
+          this.renderDetails();
+        });
+      }
+    }
+
+    // Render details
+    this.renderDetails();
+
+    // Render global todos
+    this.renderGlobalTodos();
+  }
+
+  private renderGlobalTodos(): void {
+    const globalTodosSection = this.contentEl.querySelector(".workbench-global-todos");
+    if (!globalTodosSection || !this.model.globalTodos || this.model.globalTodos.length === 0) {
+      return;
+    }
+
+    // Clear and re-render
+    const existingList = globalTodosSection.querySelector(".global-todos-list");
+    if (existingList) {
+      existingList.remove();
+    }
+
+    const todosList = globalTodosSection.createDiv({ cls: "global-todos-list" });
+
+    for (const todo of this.model.globalTodos) {
+      const todoEl = todosList.createDiv({ cls: "global-todo-item" });
+      todoEl.createEl("div", { cls: "todo-type", text: todo.type });
+      todoEl.createEl("div", { cls: "todo-description", text: todo.description });
+      todoEl.createEl("div", { cls: "todo-priority", text: `Priority: ${todo.priority}` });
+
+      // Render actions
+      const actionsContainer = todoEl.createDiv({ cls: "todo-actions" });
+      if (
+        todo.type === "dangling_target" ||
+        todo.type === "dangling_target_heading" ||
+        todo.type === "only_candidates" ||
+        todo.type === "missing_edges" ||
+        todo.type === "no_causal_roles"
+      ) {
+        const actions = (todo as any).actions || [];
+        for (const action of actions) {
+          const actionBtn = actionsContainer.createEl("button", {
+            text: this.getActionLabel(action),
+          });
+          actionBtn.addEventListener("click", () => {
+            this.handleGlobalTodoAction(todo, action);
+          });
+        }
+      } else if (todo.type === "one_sided_connectivity") {
+        // Informational only - no actions
+        actionsContainer.createEl("span", { text: "Informational only", cls: "info-text" });
+      }
+    }
+  }
+
+  private renderDetails(): void {
+    const detailsContainer = this.contentEl.querySelector(".workbench-details");
+    if (!detailsContainer) return;
+
+    detailsContainer.empty();
+    detailsContainer.createEl("h3", { text: "Details" });
+
+    if (!this.selectedMatch) {
+      detailsContainer.createEl("p", { text: "Select a match to view details" });
+      return;
+    }
+
+    const match = this.selectedMatch;
+
+    // Match info
+    detailsContainer.createEl("h4", { text: match.templateName });
+    detailsContainer.createEl("p", {
+      text: `Status: ${match.status} | Score: ${match.score} | Confidence: ${match.confidence}`,
+    });
+
+    // Slots
+    detailsContainer.createEl("h5", { text: "Slots" });
+    const slotsList = detailsContainer.createEl("ul");
+    for (const [slotId, assignment] of Object.entries(match.slotAssignments)) {
+      if (assignment) {
+        const nodeStr = assignment.heading
+          ? `${assignment.file}#${assignment.heading}`
+          : assignment.file;
+        slotsList.createEl("li", { text: `${slotId}: ${nodeStr} [${assignment.noteType}]` });
+      }
+    }
+    if (match.missingSlots.length > 0) {
+      slotsList.createEl("li", {
+        text: `Missing: ${match.missingSlots.join(", ")}`,
+        cls: "missing",
+      });
+    }
+
+    // Links
+    detailsContainer.createEl("h5", { text: "Links" });
+    detailsContainer.createEl("p", {
+      text: `${match.satisfiedLinks}/${match.requiredLinks} satisfied (${match.linksComplete ? "complete" : "incomplete"})`,
+    });
+
+    // Todos
+    detailsContainer.createEl("h5", { text: `Todos (${match.todos.length})` });
+    const todosList = detailsContainer.createEl("div", { cls: "todos-list" });
+
+    for (const todo of match.todos) {
+      const todoEl = todosList.createDiv({ cls: `todo-item todo-${todo.type}` });
+      todoEl.createEl("div", { cls: "todo-description", text: todo.description });
+      todoEl.createEl("div", { cls: "todo-priority", text: `Priority: ${todo.priority}` });
+
+      // Render actions
+      const actionsContainer = todoEl.createDiv({ cls: "todo-actions" });
+      if (
+        todo.type === "missing_slot" ||
+        todo.type === "missing_link" ||
+        todo.type === "weak_roles" ||
+        todo.type === "candidate_cleanup"
+      ) {
+        const actions = (todo as any).actions || [];
+        for (const action of actions) {
+          const actionBtn = actionsContainer.createEl("button", {
+            text: this.getActionLabel(action),
+          });
+          actionBtn.addEventListener("click", () => {
+            this.handleTodoAction(todo as WorkbenchTodoUnion, action, match);
+          });
+        }
+      }
+    }
+  }
+
+  private getStatusIcon(status: string): string {
+    switch (status) {
+      case "complete":
+        return "✓";
+      case "near_complete":
+        return "~";
+      case "partial":
+        return "○";
+      case "weak":
+        return "⚠";
+      default:
+        return "?";
+    }
+  }
+
+  private getActionLabel(action: string): string {
+    const labels: Record<string, string> = {
+      link_existing: "Link Existing",
+      create_note_via_interview: "Create Note",
+      insert_edge_forward: "Insert Edge",
+      insert_edge_inverse: "Insert Inverse",
+      choose_target_anchor: "Choose Anchor",
+      change_edge_type: "Change Type",
+      promote_candidate: "Promote",
+      resolve_candidate: "Resolve",
+      create_missing_note: "Create Missing Note",
+      retarget_link: "Retarget Link",
+      create_missing_heading: "Create Missing Heading",
+      retarget_to_existing_heading: "Retarget to Existing Heading",
+      promote_all_candidates: "Promote All Candidates",
+      create_explicit_edges: "Create Explicit Edges",
+      add_edges_to_section: "Add Edges to Section",
+    };
+    return labels[action] || action;
+  }
+
+  private async handleTodoAction(
+    todo: WorkbenchTodoUnion,
+    action: string,
+    match: WorkbenchMatch
+  ): Promise<void> {
+    console.log("[Chain Workbench] Action:", action, "for todo:", todo.type);
+
+    try {
+      const activeFile = this.app.workspace.getActiveFile();
+      const activeEditor = this.app.workspace.activeEditor?.editor;
+
+      if (!activeFile || !activeEditor) {
+        new Notice("No active file or editor");
+        return;
+      }
+
+      // Import action handlers
+      const { insertEdgeForward, promoteCandidate } = await import("../workbench/writerActions");
+      const graphSchema = await this.pluginInstance.ensureGraphSchemaLoaded();
+
+      switch (action) {
+        case "insert_edge_forward":
+          if (todo.type === "missing_link") {
+            console.log("[Chain Workbench] Starting insert_edge_forward for missing_link todo");
+            // Let user choose zone
+            console.log("[Chain Workbench] Opening zone chooser...");
+            const zoneChoice = await this.chooseZone(activeFile);
+            console.log("[Chain Workbench] Zone choice:", zoneChoice);
+            if (zoneChoice === null) {
+              console.log("[Chain Workbench] User cancelled zone selection");
+              return; // User cancelled
+            }
+
+            // Get edge vocabulary
+            console.log("[Chain Workbench] Loading edge vocabulary...");
+            const { VocabularyLoader } = await import("../vocab/VocabularyLoader");
+            const { parseEdgeVocabulary } = await import("../vocab/parseEdgeVocabulary");
+            const vocabText = await VocabularyLoader.loadText(this.app, this.settings.edgeVocabularyPath);
+            const edgeVocabulary = parseEdgeVocabulary(vocabText);
+            console.log("[Chain Workbench] Edge vocabulary loaded, entries:", edgeVocabulary.byCanonical.size);
+            
+            console.log("[Chain Workbench] Calling insertEdgeForward...");
+            try {
+              await insertEdgeForward(
+                this.app,
+                activeEditor,
+                activeFile,
+                todo,
+                this.vocabulary,
+                edgeVocabulary,
+                this.settings,
+                graphSchema,
+                zoneChoice
+              );
+              console.log("[Chain Workbench] insertEdgeForward completed successfully");
+            } catch (error) {
+              console.error("[Chain Workbench] Error in insertEdgeForward:", error);
+              new Notice(`Error inserting edge: ${error instanceof Error ? error.message : String(error)}`);
+              return;
+            }
+
+            // Re-run analysis
+            console.log("[Chain Workbench] Refreshing workbench...");
+            await this.refreshWorkbench();
+            new Notice("Edge inserted successfully");
+          }
+          break;
+
+        case "promote_candidate":
+          if (todo.type === "candidate_cleanup") {
+            await promoteCandidate(
+              this.app,
+              activeEditor,
+              activeFile,
+              todo,
+              this.settings
+            );
+
+            // Re-run analysis
+            await this.refreshWorkbench();
+            new Notice("Candidate promoted successfully");
+          }
+          break;
+
+        case "link_existing":
+          if (todo.type === "missing_slot") {
+            const { linkExisting } = await import("../workbench/linkExistingAction");
+            await linkExisting(
+              this.app,
+              activeEditor,
+              activeFile,
+              todo,
+              this.model.context
+            );
+            
+            // Re-run analysis
+            await this.refreshWorkbench();
+            new Notice("Link inserted. Re-run workbench to update slot assignments.");
+          }
+          break;
+
+        case "create_note_via_interview":
+          if (todo.type === "missing_slot") {
+            const { createNoteViaInterview } = await import("../workbench/interviewOrchestration");
+            
+            // Get interview config from plugin instance
+            let interviewConfig = null;
+            if (this.pluginInstance.ensureInterviewConfigLoaded) {
+              interviewConfig = await this.pluginInstance.ensureInterviewConfigLoaded();
+            }
+            
+            if (!interviewConfig) {
+              new Notice("Interview config not available");
+              return;
+            }
+            
+            // Find the match for this todo
+            const matchForTodo = this.model.matches.find((m) => 
+              m.todos.some((t) => t.id === todo.id)
+            );
+            
+            if (!matchForTodo) {
+              new Notice("Could not find match for todo");
+              return;
+            }
+
+            // Get edge vocabulary - we need to load it from settings
+            const { VocabularyLoader } = await import("../vocab/VocabularyLoader");
+            const { parseEdgeVocabulary } = await import("../vocab/parseEdgeVocabulary");
+            const vocabText = await VocabularyLoader.loadText(this.app, this.settings.edgeVocabularyPath);
+            const edgeVocabulary = parseEdgeVocabulary(vocabText);
+            
+            await createNoteViaInterview(
+              this.app,
+              todo,
+              matchForTodo.templateName,
+              matchForTodo,
+              interviewConfig,
+              this.chainTemplates,
+              this.chainRoles,
+              this.settings,
+              this.vocabulary,
+              edgeVocabulary,
+              this.pluginInstance
+            );
+
+            // Re-run analysis after note creation
+            await this.refreshWorkbench();
+            new Notice("Note created via interview");
+          }
+          break;
+
+        default:
+          new Notice(`Action "${action}" not yet implemented`);
+      }
+    } catch (e) {
+      const msg = e instanceof Error ? e.message : String(e);
+      console.error("[Chain Workbench] Error handling action:", e);
+      new Notice(`Failed to execute action: ${msg}`);
+    }
+  }
+
+  private async handleGlobalTodoAction(todo: WorkbenchTodoUnion, action: string): Promise<void> {
+    console.log("[Chain Workbench] Global Todo Action:", action, "for todo:", todo.type);
+
+    try {
+      const activeFile = this.app.workspace.getActiveFile();
+      const activeEditor = this.app.workspace.activeEditor?.editor;
+
+      if (!activeFile || !activeEditor) {
+        new Notice("No active file or editor");
+        return;
+      }
+
+      // Import action handlers
+      const { promoteCandidate } = await import("../workbench/writerActions");
+      const { linkExisting } = await import("../workbench/linkExistingAction");
+
+      switch (action) {
+        case "create_missing_note":
+          if (todo.type === "dangling_target") {
+            const danglingTodo = todo as any;
+            // Use linkExisting action to create note
+            await linkExisting(
+              this.app,
+              activeEditor,
+              activeFile,
+              {
+                type: "missing_slot",
+                id: `dangling_target_create_${danglingTodo.targetFile}`,
+                description: `Create missing note: ${danglingTodo.targetFile}`,
+                priority: "high",
+                slotId: "",
+                allowedNodeTypes: [],
+                actions: ["create_note_via_interview"],
+              },
+              this.model.context
+            );
+            await this.refreshWorkbench();
+            new Notice("Note creation initiated");
+          }
+          break;
+
+        case "retarget_link":
+          if (todo.type === "dangling_target") {
+            const danglingTodo = todo as any;
+            // Use linkExisting to retarget
+            await linkExisting(
+              this.app,
+              activeEditor,
+              activeFile,
+              {
+                type: "missing_slot",
+                id: `dangling_target_retarget_${danglingTodo.targetFile}`,
+                description: `Retarget link to existing note`,
+                priority: "high",
+                slotId: "",
+                allowedNodeTypes: [],
+                actions: ["link_existing"],
+              },
+              this.model.context
+            );
+            await this.refreshWorkbench();
+            new Notice("Link retargeting initiated");
+          }
+          break;
+
+        case "promote_all_candidates":
+          if (todo.type === "only_candidates") {
+            const onlyCandidatesTodo = todo as any;
+            // Promote each candidate edge
+            for (const candidateEdge of onlyCandidatesTodo.candidateEdges || []) {
+              // Find the actual edge in the graph
+              // This is a simplified version - full implementation would need to find the edge
+              new Notice(`Promoting candidate edge: ${candidateEdge.rawEdgeType}`);
+            }
+            await this.refreshWorkbench();
+            new Notice("Candidates promoted");
+          }
+          break;
+
+        case "promote_candidate":
+          // Similar to template-based promote_candidate
+          if (todo.type === "candidate_cleanup") {
+            await promoteCandidate(
+              this.app,
+              activeEditor,
+              activeFile,
+              todo,
+              this.settings
+            );
+            await this.refreshWorkbench();
+            new Notice("Candidate promoted");
+          }
+          break;
+
+        case "change_edge_type":
+          if (todo.type === "no_causal_roles" || todo.type === "weak_roles") {
+            // Use existing change_edge_type logic
+            new Notice("Change edge type - feature coming soon");
+          }
+          break;
+
+        default:
+          new Notice(`Action "${action}" not yet implemented for ${todo.type}`);
+          break;
+      }
+    } catch (e) {
+      console.error("[Chain Workbench] Error handling global todo action:", e);
+      new Notice(`Error: ${e instanceof Error ? e.message : String(e)}`);
+    }
+  }
+
+  private async chooseZone(file: any): Promise<"section" | "note_links" | "candidates" | null> {
+    console.log("[chooseZone] Starting zone selection");
+    return new Promise((resolve) => {
+      let resolved = false;
+      const { Modal, Setting } = require("obsidian");
+      const modal = new Modal(this.app);
+      modal.titleEl.textContent = "Choose Zone";
+      modal.contentEl.createEl("p", { text: "Where should the edge be inserted?" });
+
+      const doResolve = (value: "section" | "note_links" | "candidates" | null) => {
+        if (!resolved) {
+          resolved = true;
+          resolve(value);
+        }
+      };
+
+      new Setting(modal.contentEl)
+        .setName("Section-scope")
+        .setDesc("Insert in source section (standard)")
+        .addButton((btn: any) =>
+          btn.setButtonText("Select").onClick(() => {
+            console.log("[chooseZone] User selected: section");
+            doResolve("section");
+            modal.close();
+          })
+        );
+
+      new Setting(modal.contentEl)
+        .setName("Note-Verbindungen")
+        .setDesc("Insert in Note-Verbindungen zone (note-scope)")
+        .addButton((btn: any) =>
+          btn.setButtonText("Select").onClick(() => {
+            console.log("[chooseZone] User selected: note_links");
+            doResolve("note_links");
+            modal.close();
+          })
+        );
+
+      new Setting(modal.contentEl)
+        .setName("Kandidaten")
+        .setDesc("Insert in Kandidaten zone (candidate)")
+        .addButton((btn: any) =>
+          btn.setButtonText("Select").onClick(() => {
+            console.log("[chooseZone] User selected: candidates");
+            doResolve("candidates");
+            modal.close();
+          })
+        );
+
+      modal.onClose = () => {
+        console.log("[chooseZone] Modal closed, resolved:", resolved);
+        if (!resolved) {
+          console.log("[chooseZone] Resolving with null (user cancelled)");
+          doResolve(null);
+        }
+      };
+
+      console.log("[chooseZone] Opening modal...");
+      modal.open();
+    });
+  }
+
+  private async refreshWorkbench(): Promise<void> {
+    // Close and reopen workbench to refresh
+    this.close();
+    
+    // Re-run command
+    const { executeChainWorkbench } = await import("../commands/chainWorkbenchCommand");
+    const activeFile = this.app.workspace.getActiveFile();
+    const activeEditor = this.app.workspace.activeEditor?.editor;
+
+    if (activeFile && activeEditor) {
+      await executeChainWorkbench(
+        this.app,
+        activeEditor,
+        activeFile.path,
+        this.chainRoles,
+        this.chainTemplates,
+        undefined,
+        this.settings,
+        this.pluginInstance
+      );
+    }
+  }
+
+  onClose(): void {
+    const { contentEl } = this;
+    contentEl.empty();
+  }
+}

src/ui/EdgeTypeChooserModal.ts

@@ -20,19 +20,22 @@ export class EdgeTypeChooserModal extends Modal {
   private targetType: string | null;
   private graphSchema: GraphSchema | null;
   private selectedCanonical: string | null = null;
+  private suggestedTypes: string[]; // Suggested edge types from chain_roles
 
   constructor(
     app: any,
     vocabulary: EdgeVocabulary,
     sourceType: string | null,
     targetType: string | null,
-    graphSchema: GraphSchema | null = null
+    graphSchema: GraphSchema | null = null,
+    suggestedTypes: string[] = []
   ) {
     super(app);
     this.vocabulary = vocabulary;
     this.sourceType = sourceType;
     this.targetType = targetType;
     this.graphSchema = graphSchema;
+    this.suggestedTypes = suggestedTypes;
   }
 
   onOpen(): void {
@@ -57,14 +60,44 @@ export class EdgeTypeChooserModal extends Modal {
       totalEdgeTypes: allEdgeTypes.length,
       categories: Array.from(grouped.keys()),
       categorySizes: Array.from(grouped.entries()).map(([cat, types]) => ({ category: cat, count: types.length })),
+      suggestedTypes: this.suggestedTypes.length,
     });
     
-    // Recommended section (if any)
+    // PRIORITY 1: Suggested types from chain_roles (if any)
+    if (this.suggestedTypes.length > 0) {
+      contentEl.createEl("h3", { text: "🎯 Suggested (from chain)" });
+      const suggestedContainer = contentEl.createEl("div", { cls: "edge-type-list" });
+      
+      for (const canonical of this.suggestedTypes) {
+        const entry = this.vocabulary.byCanonical.get(canonical);
+        if (!entry) continue;
+        
+        // Display: canonical type (primary), aliases shown after selection
+        const btn = suggestedContainer.createEl("button", {
+          text: `🎯 ${canonical}`,
+          cls: "mod-cta",
+        });
+        
+        // Add description as tooltip/hover text
+        if (entry.description) {
+          btn.title = entry.description;
+          btn.setAttribute("data-description", entry.description);
+        }
+        
+        btn.onclick = () => {
+          this.selectEdgeType(canonical, entry.aliases);
+        };
+      }
+    }
+    
+    // PRIORITY 2: Recommended section (if any, and not already in suggested)
     if (suggestions.typical.length > 0) {
+      const notInSuggested = suggestions.typical.filter((t) => !this.suggestedTypes.includes(t));
+      if (notInSuggested.length > 0) {
         contentEl.createEl("h3", { text: "⭐ Recommended (schema)" });
         const recommendedContainer = contentEl.createEl("div", { cls: "edge-type-list" });
         
-      for (const canonical of suggestions.typical) {
+        for (const canonical of notInSuggested) {
           const entry = this.vocabulary.byCanonical.get(canonical);
           if (!entry) continue;
           
@@ -85,6 +118,7 @@ export class EdgeTypeChooserModal extends Modal {
           };
         }
       }
+    }
     
     // All categories
     if (grouped.size > 1 || (grouped.size === 1 && !grouped.has("All"))) {
@@ -105,11 +139,14 @@ export class EdgeTypeChooserModal extends Modal {
       const container = contentEl.createEl("div", { cls: "edge-type-list" });
       
       for (const { canonical, aliases, displayName, description } of types) {
+        // Skip if already shown in suggested or recommended sections
+        if (this.suggestedTypes.includes(canonical) || suggestions.typical.includes(canonical)) {
+          continue;
+        }
+        
         const isProhibited = suggestions.prohibited.includes(canonical);
-        const isTypical = suggestions.typical.includes(canonical);
         
         let prefix = "→";
-        if (isTypical) prefix = "⭐";
         if (isProhibited) prefix = "🚫";
         
         // Display: canonical type (primary), aliases shown after selection

src/ui/VaultTriageScanModal.ts

@@ -0,0 +1,362 @@
+/**
+ * Vault Triage Scan Modal - UI for vault triage scan backlog.
+ */
+
+import { Modal, Setting, Notice } from "obsidian";
+import type { App } from "obsidian";
+import type { ChainRolesConfig, ChainTemplatesConfig } from "../dictionary/types";
+import type { MindnetSettings } from "../settings";
+import type { EdgeVocabulary } from "../vocab/types";
+import { scanVaultForChainGaps, saveScanState, type ScanState, type ScanItem } from "../workbench/vaultTriageScan";
+
+export class VaultTriageScanModal extends Modal {
+  private chainRoles: ChainRolesConfig | null;
+  private chainTemplates: ChainTemplatesConfig | null;
+  private edgeVocabulary: EdgeVocabulary | null;
+  private settings: MindnetSettings;
+  private pluginInstance: any;
+  private existingState: ScanState | null;
+
+  private items: ScanItem[] = [];
+  private filterStatus: string | null = null;
+  private filterHasMissingSlot: boolean = false;
+  private filterHasMissingLink: boolean = false;
+  private filterWeak: boolean = false;
+  private filterCandidateCleanup: boolean = false;
+  private searchQuery: string = "";
+  private isScanning: boolean = false;
+  private shouldCancel: boolean = false;
+
+  constructor(
+    app: App,
+    chainRoles: ChainRolesConfig | null,
+    chainTemplates: ChainTemplatesConfig | null,
+    edgeVocabulary: EdgeVocabulary | null,
+    settings: MindnetSettings,
+    pluginInstance: any,
+    existingState: ScanState | null
+  ) {
+    super(app);
+    this.chainRoles = chainRoles;
+    this.chainTemplates = chainTemplates;
+    this.edgeVocabulary = edgeVocabulary;
+    this.settings = settings;
+    this.pluginInstance = pluginInstance;
+    this.existingState = existingState;
+    
+    if (existingState) {
+      this.items = existingState.items;
+    }
+  }
+
+  onOpen(): void {
+    const { contentEl } = this;
+    contentEl.empty();
+
+    // Header
+    contentEl.createEl("h2", { text: "Vault Triage Scan" });
+    
+    if (this.existingState && !this.existingState.completed) {
+      contentEl.createEl("p", {
+        text: `Resuming scan: ${this.existingState.progress.current}/${this.existingState.progress.total}`,
+        cls: "scan-progress-info",
+      });
+    }
+
+    // Controls
+    const controlsContainer = contentEl.createDiv({ cls: "scan-controls" });
+    
+    // Start/Resume scan button
+    if (!this.isScanning && (this.items.length === 0 || !this.existingState?.completed)) {
+      const scanBtn = controlsContainer.createEl("button", {
+        text: this.items.length === 0 ? "Start Scan" : "Resume Scan",
+        cls: "mod-cta",
+      });
+      scanBtn.addEventListener("click", () => {
+        this.startScan();
+      });
+    }
+
+    // Filters
+    const filtersContainer = contentEl.createDiv({ cls: "scan-filters" });
+    filtersContainer.createEl("h3", { text: "Filters" });
+
+    // Status filter
+    const statusSelect = filtersContainer.createEl("select");
+    statusSelect.createEl("option", { text: "All", value: "" });
+    statusSelect.createEl("option", { text: "Near Complete", value: "near_complete" });
+    statusSelect.createEl("option", { text: "Partial", value: "partial" });
+    statusSelect.createEl("option", { text: "Weak", value: "weak" });
+    statusSelect.createEl("option", { text: "Deprioritized", value: "deprioritized" });
+    statusSelect.value = this.filterStatus || "";
+    statusSelect.addEventListener("change", (e) => {
+      const target = e.target as HTMLSelectElement;
+      this.filterStatus = target.value || null;
+      this.render();
+    });
+
+    // Gap filters
+    new Setting(filtersContainer)
+      .setName("Has Missing Slot")
+      .addToggle((toggle) => {
+        toggle.setValue(this.filterHasMissingSlot);
+        toggle.onChange((value) => {
+          this.filterHasMissingSlot = value;
+          this.render();
+        });
+      });
+
+    new Setting(filtersContainer)
+      .setName("Has Missing Link")
+      .addToggle((toggle) => {
+        toggle.setValue(this.filterHasMissingLink);
+        toggle.onChange((value) => {
+          this.filterHasMissingLink = value;
+          this.render();
+        });
+      });
+
+    new Setting(filtersContainer)
+      .setName("Weak")
+      .addToggle((toggle) => {
+        toggle.setValue(this.filterWeak);
+        toggle.onChange((value) => {
+          this.filterWeak = value;
+          this.render();
+        });
+      });
+
+    new Setting(filtersContainer)
+      .setName("Candidate Cleanup")
+      .addToggle((toggle) => {
+        toggle.setValue(this.filterCandidateCleanup);
+        toggle.onChange((value) => {
+          this.filterCandidateCleanup = value;
+          this.render();
+        });
+      });
+
+    // Search
+    filtersContainer.createEl("label", { text: "Search:" });
+    const searchInput = filtersContainer.createEl("input", {
+      type: "text",
+      placeholder: "File name, heading, template...",
+    });
+    searchInput.value = this.searchQuery;
+    searchInput.addEventListener("input", (e) => {
+      const target = e.target as HTMLInputElement;
+      this.searchQuery = target.value.toLowerCase();
+      this.render();
+    });
+
+    // Results list
+    const resultsContainer = contentEl.createDiv({ cls: "scan-results" });
+    resultsContainer.createEl("h3", { text: "Results" });
+
+    this.render();
+  }
+
+  private async startScan(): Promise<void> {
+    this.isScanning = true;
+    this.shouldCancel = false;
+    this.render();
+
+    try {
+      const items = await scanVaultForChainGaps(
+        this.app,
+        this.chainRoles,
+        this.chainTemplates,
+        this.edgeVocabulary,
+        this.settings,
+        (progress) => {
+          // Update progress
+          const state: ScanState = {
+            items: this.items,
+            timestamp: Date.now(),
+            progress,
+            completed: false,
+          };
+          saveScanState(this.app, state, this.pluginInstance);
+          this.render();
+        },
+        () => this.shouldCancel
+      );
+
+      this.items = items;
+
+      // Save completed state
+      const state: ScanState = {
+        items,
+        timestamp: Date.now(),
+        progress: {
+          current: items.length,
+          total: items.length,
+          currentFile: null,
+        },
+        completed: true,
+      };
+      await saveScanState(this.app, state, this.pluginInstance);
+
+      this.isScanning = false;
+      this.render();
+    } catch (e) {
+      this.isScanning = false;
+      const msg = e instanceof Error ? e.message : String(e);
+      console.error("[Vault Triage Scan] Error:", e);
+      new Notice(`Scan failed: ${msg}`);
+      this.render();
+    }
+  }
+
+  private render(): void {
+    const resultsContainer = this.contentEl.querySelector(".scan-results");
+    if (!resultsContainer) return;
+
+    // Clear previous results
+    const existingList = resultsContainer.querySelector(".scan-items-list");
+    if (existingList) {
+      existingList.remove();
+    }
+
+    // Filter items
+    let filteredItems = this.items;
+    
+    if (this.filterStatus) {
+      filteredItems = filteredItems.filter((item) => item.status === this.filterStatus);
+    }
+    
+    if (this.filterHasMissingSlot) {
+      filteredItems = filteredItems.filter((item) => item.gapCounts.missingSlots > 0);
+    }
+    
+    if (this.filterHasMissingLink) {
+      filteredItems = filteredItems.filter((item) => item.gapCounts.missingLinks > 0);
+    }
+    
+    if (this.filterWeak) {
+      filteredItems = filteredItems.filter((item) => item.status === "weak");
+    }
+    
+    if (this.filterCandidateCleanup) {
+      filteredItems = filteredItems.filter((item) => item.gapCounts.candidateCleanup > 0);
+    }
+    
+    if (this.searchQuery) {
+      filteredItems = filteredItems.filter((item) => {
+        const fileMatch = item.file.toLowerCase().includes(this.searchQuery);
+        const headingMatch = item.heading?.toLowerCase().includes(this.searchQuery);
+        const templateMatch = item.matches.some((m) =>
+          m.templateName.toLowerCase().includes(this.searchQuery)
+        );
+        return fileMatch || headingMatch || templateMatch;
+      });
+    }
+
+    // Sort: near_complete first, then by score descending
+    filteredItems.sort((a, b) => {
+      if (a.status === "near_complete" && b.status !== "near_complete") return -1;
+      if (a.status !== "near_complete" && b.status === "near_complete") return 1;
+      
+      const aMaxScore = Math.max(...a.matches.map((m) => m.score));
+      const bMaxScore = Math.max(...b.matches.map((m) => m.score));
+      return bMaxScore - aMaxScore;
+    });
+
+    // Render list
+    const listContainer = resultsContainer.createDiv({ cls: "scan-items-list" });
+    listContainer.createEl("p", {
+      text: `${filteredItems.length} item(s)${this.isScanning ? " (scanning...)" : ""}`,
+    });
+
+    for (const item of filteredItems) {
+      const itemEl = listContainer.createDiv({ cls: "scan-item" });
+      
+      const headerEl = itemEl.createDiv({ cls: "scan-item-header" });
+      headerEl.createEl("div", {
+        cls: "scan-item-title",
+        text: `${item.file}${item.heading ? `#${item.heading}` : ""}`,
+      });
+      
+      const statusBadge = headerEl.createEl("span", {
+        cls: `scan-item-status status-${item.status}`,
+        text: item.status,
+      });
+      
+      // Gap counts
+      const gapCountsEl = itemEl.createDiv({ cls: "scan-item-gaps" });
+      if (item.gapCounts.missingSlots > 0) {
+        gapCountsEl.createEl("span", {
+          text: `Missing Slots: ${item.gapCounts.missingSlots}`,
+          cls: "gap-badge",
+        });
+      }
+      if (item.gapCounts.missingLinks > 0) {
+        gapCountsEl.createEl("span", {
+          text: `Missing Links: ${item.gapCounts.missingLinks}`,
+          cls: "gap-badge",
+        });
+      }
+      if (item.gapCounts.weakRoles > 0) {
+        gapCountsEl.createEl("span", {
+          text: `Weak Roles: ${item.gapCounts.weakRoles}`,
+          cls: "gap-badge",
+        });
+      }
+      if (item.gapCounts.candidateCleanup > 0) {
+        gapCountsEl.createEl("span", {
+          text: `Candidate Cleanup: ${item.gapCounts.candidateCleanup}`,
+          cls: "gap-badge",
+        });
+      }
+      
+      // Matches summary
+      const matchesEl = itemEl.createDiv({ cls: "scan-item-matches" });
+      matchesEl.createEl("div", {
+        text: `${item.matches.length} template match(es)`,
+      });
+      
+      // Actions
+      const actionsEl = itemEl.createDiv({ cls: "scan-item-actions" });
+      const openBtn = actionsEl.createEl("button", {
+        text: "Open Workbench",
+      });
+      openBtn.addEventListener("click", async () => {
+        // Open file and section, then open workbench
+        await this.app.workspace.openLinkText(item.file, "", true);
+        
+        // Wait a bit for file to open, then trigger workbench
+        setTimeout(async () => {
+          const { executeChainWorkbench } = await import("../commands/chainWorkbenchCommand");
+          const activeFile = this.app.workspace.getActiveFile();
+          const activeEditor = this.app.workspace.activeEditor?.editor;
+          
+          if (activeFile && activeEditor) {
+            await executeChainWorkbench(
+              this.app,
+              activeEditor,
+              activeFile.path,
+              this.chainRoles,
+              this.chainTemplates,
+              undefined,
+              this.settings,
+              this.pluginInstance
+            );
+          }
+        }, 500);
+      });
+      
+      const deprioritizeBtn = actionsEl.createEl("button", {
+        text: item.status === "deprioritized" ? "Prioritize" : "Deprioritize",
+      });
+      deprioritizeBtn.addEventListener("click", () => {
+        item.status = item.status === "deprioritized" ? "near_complete" : "deprioritized";
+        this.render();
+      });
+    }
+  }
+
+  onClose(): void {
+    const { contentEl } = this;
+    contentEl.empty();
+  }
+}

src/workbench/interviewOrchestration.ts

@@ -0,0 +1,369 @@
+/**
+ * Interview orchestration for workbench missing_slot todos.
+ */
+
+import { Notice } from "obsidian";
+import type { App, TFile } from "obsidian";
+import type { MissingSlotTodo } from "./types";
+import type { InterviewConfig, InterviewProfile } from "../interview/types";
+import type { ChainTemplatesConfig } from "../dictionary/types";
+import type { MindnetSettings } from "../settings";
+import { ProfileSelectionModal } from "../ui/ProfileSelectionModal";
+import { startWizardAfterCreate } from "../unresolvedLink/unresolvedLinkHandler";
+import { writeFrontmatter } from "../interview/writeFrontmatter";
+import { joinFolderAndBasename, ensureUniqueFilePath, ensureFolderExists } from "../mapping/folderHelpers";
+import type { Vocabulary } from "../vocab/Vocabulary";
+import { resolveCanonicalEdgeType } from "../analysis/chainInspector";
+import type { EdgeVocabulary } from "../vocab/types";
+
+export interface InterviewOrchestrationPayload {
+  templateName: string;
+  slotId: string;
+  requiredEdges: Array<{
+    edgeType: string; // Canonical edge type
+    targetNote: string; // Note file path or basename
+    targetHeading: string | null; // Heading if available
+    suggestedAlias?: string; // Optional alias suggestion
+  }>;
+}
+
+/**
+ * Create note via interview for missing slot.
+ */
+export async function createNoteViaInterview(
+  app: App,
+  todo: MissingSlotTodo,
+  matchTemplateName: string,
+  match: import("../analysis/chainInspector").TemplateMatch,
+  interviewConfig: InterviewConfig | null,
+  chainTemplates: ChainTemplatesConfig | null,
+  chainRoles: import("../dictionary/types").ChainRolesConfig | null,
+  settings: MindnetSettings,
+  vocabulary: import("../vocab/Vocabulary").Vocabulary,
+  edgeVocabulary: EdgeVocabulary | null,
+  pluginInstance: any
+): Promise<void> {
+  if (!interviewConfig) {
+    throw new Error("Interview config required");
+  }
+
+  // Find template to get required edges for this slot
+  const template = chainTemplates?.templates.find((t) => t.name === matchTemplateName);
+  if (!template) {
+    throw new Error(`Template not found: ${matchTemplateName}`);
+  }
+
+  // Get required edges for this slot
+  const requiredEdges = getRequiredEdgesForSlot(
+    template,
+    todo.slotId,
+    match,
+    chainRoles,
+    vocabulary,
+    edgeVocabulary
+  );
+
+  // Filter profiles by allowed node types
+  const allowedProfiles = interviewConfig.profiles.filter((profile) => {
+    if (todo.allowedNodeTypes.length === 0) {
+      return true; // No restrictions
+    }
+    return todo.allowedNodeTypes.includes(profile.note_type);
+  });
+
+  if (allowedProfiles.length === 0) {
+    throw new Error(`No interview profiles found for node types: ${todo.allowedNodeTypes.join(", ")}`);
+  }
+
+  // Let user select profile
+  const profileResult = await selectProfile(
+    app,
+    interviewConfig,
+    allowedProfiles,
+    settings
+  );
+
+  if (!profileResult) {
+    return; // User cancelled
+  }
+
+  // Build payload for interview
+  const payload: InterviewOrchestrationPayload = {
+    templateName: matchTemplateName,
+    slotId: todo.slotId,
+    requiredEdges: requiredEdges.map((edge) => ({
+      edgeType: edge.edgeType,
+      targetNote: edge.targetNote,
+      targetHeading: edge.targetHeading,
+      suggestedAlias: edge.suggestedAlias,
+    })),
+  };
+
+  // Create note with minimal structure
+  const id = `note_${Date.now()}_${Math.random().toString(36).substring(2, 9)}`;
+  const frontmatter = writeFrontmatter({
+    id,
+    title: profileResult.title,
+    noteType: profileResult.profile.note_type,
+    interviewProfile: profileResult.profile.key,
+    defaults: profileResult.profile.defaults,
+    frontmatterWhitelist: interviewConfig.frontmatterWhitelist,
+  });
+
+  // Build content with zones
+  let content = `${frontmatter}\n\n`;
+  if (settings.fixActions.createMissingNote.includeZones === "note_links_only" || 
+      settings.fixActions.createMissingNote.includeZones === "both") {
+    content += "## Note-Verbindungen\n\n";
+  }
+  if (settings.fixActions.createMissingNote.includeZones === "candidates_only" || 
+      settings.fixActions.createMissingNote.includeZones === "both") {
+    content += "## Kandidaten\n\n";
+  }
+
+  // Ensure folder exists
+  const folderPath = profileResult.folderPath || settings.defaultNotesFolder || "";
+  if (folderPath) {
+    await ensureFolderExists(app, folderPath);
+  }
+
+  // Build file path
+  const fileName = `${profileResult.title}.md`;
+  const desiredPath = joinFolderAndBasename(folderPath, fileName);
+  const filePath = await ensureUniqueFilePath(app, desiredPath);
+
+  // Create file
+  const file = await app.vault.create(filePath, content);
+
+  // Open file
+  await app.workspace.openLinkText(filePath, "", true);
+
+  // Convert payload.requiredEdges to PendingEdgeAssignment format for wizard
+  // The wizard will use these as quick-insert options
+  const pendingEdgeAssignments = payload.requiredEdges.map((edge) => {
+    // Get section key for target note (we'll use ROOT for now, could be improved)
+    const sectionKey = edge.targetHeading ? `H2:${edge.targetHeading}` : "ROOT";
+    
+    return {
+      filePath: file.path,
+      sectionKey: "ROOT", // Source section (new note, root section)
+      linkBasename: edge.targetNote,
+      chosenRawType: edge.suggestedAlias || edge.edgeType, // Use alias if available, otherwise canonical
+      createdAt: Date.now(),
+    };
+  });
+
+  // Start wizard with payload
+  // Note: The wizard system doesn't directly accept pendingEdgeAssignments in startWizardAfterCreate
+  // We'll need to inject them into the wizard state after creation
+  // For now, we'll rely on soft validation after wizard completion
+  await startWizardAfterCreate(
+    app,
+    settings,
+    file,
+    profileResult.profile,
+    content,
+    false,
+    async (result) => {
+      // Soft validation: check if requiredEdges are set
+      await validateRequiredEdges(
+        app,
+        file,
+        payload,
+        vocabulary,
+        edgeVocabulary
+      );
+      new Notice("Wizard completed");
+    },
+    async (result) => {
+      // Soft validation on save too
+      await validateRequiredEdges(
+        app,
+        file,
+        payload,
+        vocabulary,
+        edgeVocabulary
+      );
+      new Notice("Wizard saved");
+    },
+    pluginInstance
+  );
+  
+  // TODO: Inject pendingEdgeAssignments into wizard state
+  // This would require modifying InterviewWizardModal to accept initial pendingEdgeAssignments
+  // For MVP, we rely on soft validation and user can manually add edges
+}
+
+/**
+ * Get required edges for a slot from template and match context.
+ */
+function getRequiredEdgesForSlot(
+  template: import("../dictionary/types").ChainTemplate,
+  slotId: string,
+  match: import("../analysis/chainInspector").TemplateMatch,
+  chainRoles: import("../dictionary/types").ChainRolesConfig | null,
+  vocabulary: Vocabulary,
+  edgeVocabulary: EdgeVocabulary | null
+): Array<{
+  edgeType: string;
+  targetNote: string;
+  targetHeading: string | null;
+  suggestedAlias?: string;
+}> {
+  const requiredEdges: Array<{
+    edgeType: string;
+    targetNote: string;
+    targetHeading: string | null;
+    suggestedAlias?: string;
+  }> = [];
+
+  // Find links that target this slot (incoming edges)
+  const normalizedLinks = template.links || [];
+  for (const link of normalizedLinks) {
+    if (link.to === slotId) {
+      // This link targets our slot
+      // Find source slot assignment to get the source note
+      const sourceAssignment = match.slotAssignments[link.from];
+      
+      if (!sourceAssignment) {
+        // Source slot not filled yet, skip
+        continue;
+      }
+
+      // Get suggested edge types from chain_roles for allowed_edge_roles
+      const suggestedEdgeTypes: string[] = [];
+      if (chainRoles && link.allowed_edge_roles) {
+        for (const roleName of link.allowed_edge_roles) {
+          const role = chainRoles.roles[roleName];
+          if (role && role.edge_types) {
+            suggestedEdgeTypes.push(...role.edge_types);
+          }
+        }
+      }
+
+      // Use first suggested type as default (canonical)
+      const defaultEdgeType = suggestedEdgeTypes[0] || "related_to";
+      
+      // Get alias suggestion if available
+      let suggestedAlias: string | undefined;
+      if (edgeVocabulary) {
+        const entry = edgeVocabulary.byCanonical.get(defaultEdgeType);
+        if (entry && entry.aliases.length > 0) {
+          suggestedAlias = entry.aliases[0];
+        }
+      }
+
+      // Build target link format
+      const targetNote = sourceAssignment.file.replace(/\.md$/, "");
+      const targetHeading = sourceAssignment.heading || null;
+
+      requiredEdges.push({
+        edgeType: defaultEdgeType,
+        targetNote,
+        targetHeading,
+        suggestedAlias,
+      });
+    }
+  }
+
+  return requiredEdges;
+}
+
+/**
+ * Select interview profile.
+ */
+async function selectProfile(
+  app: App,
+  interviewConfig: InterviewConfig,
+  allowedProfiles: InterviewProfile[],
+  settings: MindnetSettings
+): Promise<{ profile: InterviewProfile; title: string; folderPath: string } | null> {
+  return new Promise((resolve) => {
+    // Filter config to only allowed profiles
+    const filteredConfig: InterviewConfig = {
+      ...interviewConfig,
+      profiles: allowedProfiles,
+    };
+    
+    // Use ProfileSelectionModal with filtered profiles
+    const modal = new ProfileSelectionModal(
+      app,
+      filteredConfig,
+      async (result) => {
+        resolve({
+          profile: result.profile,
+          title: result.title,
+          folderPath: result.folderPath || settings.defaultNotesFolder || "",
+        });
+      },
+      "", // Default title (user will set)
+      settings.defaultNotesFolder || ""
+    );
+
+    // Filter profiles in modal (we'll need to modify ProfileSelectionModal or filter here)
+    // For now, we'll pass all profiles and let user choose
+    modal.onClose = () => {
+      resolve(null);
+    };
+    modal.open();
+  });
+}
+
+/**
+ * Soft validation: check if requiredEdges are set.
+ */
+async function validateRequiredEdges(
+  app: App,
+  file: TFile,
+  payload: InterviewOrchestrationPayload,
+  vocabulary: Vocabulary,
+  edgeVocabulary: EdgeVocabulary | null
+): Promise<void> {
+  const content = await app.vault.read(file);
+  
+  // Parse edges from content
+  const { parseEdgesFromCallouts } = await import("../parser/parseEdgesFromCallouts");
+  const parsedEdges = parseEdgesFromCallouts(content);
+
+  // Check each required edge
+  const missingEdges: string[] = [];
+  
+  for (const requiredEdge of payload.requiredEdges) {
+    // Skip if targetNote is empty (not yet determined from context)
+    if (!requiredEdge.targetNote) {
+      continue;
+    }
+
+    // Check if edge exists
+    const edgeExists = parsedEdges.some((parsedEdge) => {
+      // Check canonical edge type match
+      const canonical = edgeVocabulary
+        ? resolveCanonicalEdgeType(parsedEdge.rawType, edgeVocabulary).canonical
+        : null;
+
+      if (!canonical || canonical !== requiredEdge.edgeType) {
+        return false;
+      }
+
+      // Check target match
+      return parsedEdge.targets.some((target) => {
+        const normalizedTarget = target.split("#")[0]?.split("|")[0]?.trim() || target;
+        return normalizedTarget === requiredEdge.targetNote;
+      });
+    });
+
+    if (!edgeExists) {
+      missingEdges.push(
+        `${requiredEdge.edgeType} -> ${requiredEdge.targetNote}${requiredEdge.targetHeading ? `#${requiredEdge.targetHeading}` : ""}`
+      );
+    }
+  }
+
+  if (missingEdges.length > 0 && app.workspace.getActiveFile()?.path === file.path) {
+    // Show soft validation notice (not blocking)
+    new Notice(
+      `Note created, but ${missingEdges.length} required edge(s) still missing: ${missingEdges.slice(0, 2).join(", ")}${missingEdges.length > 2 ? "..." : ""}`,
+      5000
+    );
+  }
+}

src/workbench/linkExistingAction.ts

@@ -0,0 +1,78 @@
+/**
+ * Link existing action for missing_slot todos.
+ */
+
+import { Notice } from "obsidian";
+import type { App, Editor, TFile } from "obsidian";
+import type { MissingSlotTodo } from "./types";
+import { EntityPickerModal } from "../ui/EntityPickerModal";
+import { NoteIndex } from "../entityPicker/noteIndex";
+import { findSection } from "./zoneDetector";
+
+/**
+ * Link existing note/section to fill missing slot.
+ */
+export async function linkExisting(
+  app: App,
+  editor: Editor,
+  file: TFile,
+  todo: MissingSlotTodo,
+  context: { file: string; heading: string | null }
+): Promise<void> {
+  // Show note picker
+  const noteIndex = new NoteIndex(app);
+  
+  const selectedNote = await new Promise<{ basename: string; path: string } | null>(
+    (resolve) => {
+      const modal = new EntityPickerModal(
+        app,
+        noteIndex,
+        (result) => {
+          modal.close();
+          resolve(result);
+        }
+      );
+      modal.onClose = () => {
+        resolve(null);
+      };
+      modal.open();
+    }
+  );
+
+  if (!selectedNote) {
+    return; // User cancelled
+  }
+
+  // Filter by allowed node types if specified
+  // For now, we'll just show all notes and let user choose
+  // TODO: Filter noteIndex by noteType if allowedNodeTypes specified
+
+  // User selected a note, now we need to:
+  // 1. Determine if they want to link to a specific section or the whole note
+  // 2. Insert the link in the current section
+  
+  // For now, we'll insert a simple link
+  // The actual slot assignment would need to be done via template matching
+  // This is a placeholder - the real implementation would need to update the match
+  
+  const targetNote = selectedNote.basename.replace(/\.md$/, "");
+  const linkText = `[[${targetNote}]]`;
+  
+  // Insert link at cursor position
+  const cursor = editor.getCursor();
+  const line = editor.getLine(cursor.line);
+  const beforeCursor = line.substring(0, cursor.ch);
+  const afterCursor = line.substring(cursor.ch);
+  
+  // Insert link
+  const newLine = beforeCursor + linkText + afterCursor;
+  editor.setLine(cursor.line, newLine);
+  
+  // Move cursor after link
+  editor.setCursor({
+    line: cursor.line,
+    ch: cursor.ch + linkText.length,
+  });
+  
+  new Notice(`Linked to ${targetNote}. Note: This is a placeholder - slot assignment requires re-running workbench.`);
+}

src/workbench/statusCalculator.ts

@@ -0,0 +1,99 @@
+/**
+ * Calculate match status for workbench matches.
+ */
+
+import type { TemplateMatch } from "../analysis/chainInspector";
+import type { MatchStatus, WorkbenchMatch } from "./types";
+
+/**
+ * Calculate status for a template match.
+ */
+export function calculateMatchStatus(match: TemplateMatch, hasWeakRoles: boolean): MatchStatus {
+  const slotsFilled = Object.keys(match.slotAssignments).length;
+  const slotsTotal = slotsFilled + match.missingSlots.length;
+  const linksSatisfied = match.satisfiedLinks;
+  const linksRequired = match.requiredLinks;
+
+  // complete: slotsFilled==slotsTotal && linksSatisfied==linksRequired
+  if (slotsFilled === slotsTotal && linksSatisfied === linksRequired) {
+    return "complete";
+  }
+
+  // near_complete:
+  // a) slotsFilled==slotsTotal && (linksRequired-linksSatisfied) in {1,2}
+  // ODER
+  // b) (slotsTotal-slotsFilled)==1 && linksSatisfied==linksRequired
+  if (
+    (slotsFilled === slotsTotal && linksRequired - linksSatisfied >= 1 && linksRequired - linksSatisfied <= 2) ||
+    (slotsTotal - slotsFilled === 1 && linksSatisfied === linksRequired)
+  ) {
+    return "near_complete";
+  }
+
+  // weak:
+  // Match vorhanden, aber Findings enthalten weak_chain_roles / no_causal_roles
+  // oder die erfüllten Verbindungen sind überwiegend structural/temporal ohne causal/constraints
+  if (hasWeakRoles) {
+    return "weak";
+  }
+
+  // partial: sonstige Fälle mit mindestens einer Lücke
+  return "partial";
+}
+
+/**
+ * Calculate slots filled/total for a match.
+ */
+export function calculateSlotsStats(match: TemplateMatch): { filled: number; total: number } {
+  const filled = Object.keys(match.slotAssignments).length;
+  const total = filled + match.missingSlots.length;
+  return { filled, total };
+}
+
+/**
+ * Check if match has weak roles.
+ */
+export function hasWeakRoles(match: TemplateMatch): boolean {
+  // Check roleEvidence: if all roles are structural/temporal and no causal/constraints
+  if (!match.roleEvidence || match.roleEvidence.length === 0) {
+    return false;
+  }
+
+  const causalRoles = ["causal", "influences", "enables_constraints"];
+  const structuralTemporalRoles = ["structural", "temporal", "epistemic", "normative"];
+
+  const hasCausalRole = match.roleEvidence.some((ev) => causalRoles.includes(ev.edgeRole));
+  const allStructuralTemporal = match.roleEvidence.every((ev) =>
+    structuralTemporalRoles.includes(ev.edgeRole)
+  );
+
+  // Weak if no causal roles and all are structural/temporal
+  return !hasCausalRole && allStructuralTemporal;
+}
+
+/**
+ * Determine effective required_links value.
+ */
+export function getEffectiveRequiredLinks(
+  match: TemplateMatch,
+  profileRequiredLinks?: boolean,
+  templateRequiredLinks?: boolean,
+  defaultRequiredLinks?: boolean
+): boolean {
+  // Resolution Order:
+  // 1. template.matching?.required_links
+  // 2. profile.required_links
+  // 3. defaults.matching?.required_links
+  // 4. Fallback: false
+
+  if (templateRequiredLinks !== undefined) {
+    return templateRequiredLinks;
+  }
+  if (profileRequiredLinks !== undefined) {
+    return profileRequiredLinks;
+  }
+  if (defaultRequiredLinks !== undefined) {
+    return defaultRequiredLinks;
+  }
+  return false;
+}

src/workbench/todoGenerator.ts

@@ -0,0 +1,491 @@
+/**
+ * Generate todos for workbench matches.
+ */
+
+import type { App } from "obsidian";
+import type { TemplateMatch, NeighborEdge, Finding } from "../analysis/chainInspector";
+import type { IndexedEdge } from "../analysis/graphIndex";
+import type { ChainRolesConfig, ChainTemplatesConfig } from "../dictionary/types";
+import type {
+  WorkbenchTodoUnion,
+  MissingSlotTodo,
+  MissingLinkTodo,
+  WeakRolesTodo,
+  CandidateCleanupTodo,
+  DanglingTargetTodo,
+  DanglingTargetHeadingTodo,
+  OnlyCandidatesTodo,
+  MissingEdgesTodo,
+  NoCausalRolesTodo,
+  OneSidedConnectivityTodo,
+} from "./types";
+import { resolveCanonicalEdgeType } from "../analysis/chainInspector";
+import type { EdgeVocabulary } from "../vocab/types";
+
+/**
+ * Generate todos for a template match.
+ */
+export async function generateTodos(
+  app: App,
+  match: TemplateMatch,
+  template: import("../dictionary/types").ChainTemplate,
+  chainRoles: ChainRolesConfig | null,
+  edgeVocabulary: EdgeVocabulary | null,
+  allEdges: IndexedEdge[],
+  candidateEdges: IndexedEdge[],
+  confirmedEdges: IndexedEdge[],
+  context: { file: string; heading: string | null }
+): Promise<WorkbenchTodoUnion[]> {
+  const todos: WorkbenchTodoUnion[] = [];
+
+  // 1. Missing slot todos
+  for (const slotId of match.missingSlots) {
+    const slot = template.slots.find((s) => (typeof s === "string" ? s === slotId : s.id === slotId));
+    if (slot) {
+      const allowedNodeTypes = typeof slot === "string" ? [] : slot.allowed_node_types || [];
+      todos.push({
+        type: "missing_slot",
+        id: `missing_slot_${match.templateName}_${slotId}`,
+        description: `Missing slot "${slotId}" for template "${match.templateName}"`,
+        priority: "high",
+        slotId,
+        allowedNodeTypes,
+        actions: ["link_existing", "create_note_via_interview"],
+      } as MissingSlotTodo);
+    }
+  }
+
+  // 2. Missing link todos
+  // Get normalized template links
+  const normalizedLinks = template.links || [];
+  const normalizedSlots = template.slots.map((s) =>
+    typeof s === "string" ? { id: s, allowed_node_types: [] } : s
+  );
+
+  for (const link of normalizedLinks) {
+    const fromSlot = normalizedSlots.find((s) => s.id === link.from);
+    const toSlot = normalizedSlots.find((s) => s.id === link.to);
+
+    if (!fromSlot || !toSlot) continue;
+
+    const fromAssignment = match.slotAssignments[link.from];
+    const toAssignment = match.slotAssignments[link.to];
+
+    // Only generate todo if both slots are filled but link is missing
+    if (fromAssignment && toAssignment) {
+      // Check if link exists in roleEvidence
+      // roleEvidence uses slot IDs (e.g., "learning", "behavior"), not file paths
+      const linkExists = match.roleEvidence?.some(
+        (ev) =>
+          ev.from === link.from && ev.to === link.to
+      );
+
+      console.log(`[todoGenerator] Checking link ${link.from} -> ${link.to}:`, {
+        linkExists,
+        roleEvidence: match.roleEvidence?.filter(ev => ev.from === link.from && ev.to === link.to)
+      });
+
+      if (!linkExists) {
+        // Get suggested edge types from chain_roles for allowed_edge_roles
+        const suggestedEdgeTypes: string[] = [];
+        if (chainRoles && link.allowed_edge_roles) {
+          for (const roleName of link.allowed_edge_roles) {
+            const role = chainRoles.roles[roleName];
+            if (role && role.edge_types) {
+              suggestedEdgeTypes.push(...role.edge_types);
+            }
+          }
+        }
+
+        todos.push({
+          type: "missing_link",
+          id: `missing_link_${match.templateName}_${link.from}_${link.to}`,
+          description: `Missing link from "${link.from}" to "${link.to}" for template "${match.templateName}"`,
+          priority: "high",
+          fromSlotId: link.from,
+          toSlotId: link.to,
+          fromNodeRef: {
+            file: fromAssignment.file,
+            heading: fromAssignment.heading || null,
+            noteType: fromAssignment.noteType,
+          },
+          toNodeRef: {
+            file: toAssignment.file,
+            heading: toAssignment.heading || null,
+            noteType: toAssignment.noteType,
+          },
+          allowedEdgeRoles: link.allowed_edge_roles || [],
+          suggestedEdgeTypes: [...new Set(suggestedEdgeTypes)], // Deduplicate
+          actions: ["insert_edge_forward", "insert_edge_inverse", "choose_target_anchor"],
+        } as MissingLinkTodo);
+      }
+    }
+  }
+
+  // 3. Weak roles todos
+  if (match.roleEvidence && match.roleEvidence.length > 0) {
+    const causalRoles = ["causal", "influences", "enables_constraints"];
+    const hasCausalRole = match.roleEvidence.some((ev) => causalRoles.includes(ev.edgeRole));
+
+    if (!hasCausalRole) {
+      // Check if all roles are structural/temporal
+      const structuralTemporalRoles = ["structural", "temporal", "epistemic", "normative"];
+      const allStructuralTemporal = match.roleEvidence.every((ev) =>
+        structuralTemporalRoles.includes(ev.edgeRole)
+      );
+
+      if (allStructuralTemporal) {
+        const weakEdges = match.roleEvidence.map((ev) => {
+          // Find corresponding edge in allEdges
+          const edge = allEdges.find(
+            (e) =>
+              e.rawEdgeType === ev.rawEdgeType &&
+              `${e.source.file}:${"sectionHeading" in e.source ? e.source.sectionHeading || "" : ""}` === ev.from &&
+              `${e.target.file}:${e.target.heading || ""}` === ev.to
+          );
+
+          return {
+            rawEdgeType: ev.rawEdgeType,
+            from: edge
+              ? "sectionHeading" in edge.source
+                ? { file: edge.source.file, heading: edge.source.sectionHeading }
+                : { file: edge.source.file, heading: null }
+              : { file: "", heading: null },
+            to: edge ? edge.target : { file: "", heading: null },
+            currentRole: ev.edgeRole,
+            suggestedRoles: causalRoles,
+          };
+        });
+
+        todos.push({
+          type: "weak_roles",
+          id: `weak_roles_${match.templateName}`,
+          description: `Template "${match.templateName}" has only structural/temporal roles, no causal roles`,
+          priority: "medium",
+          edges: weakEdges,
+          actions: ["change_edge_type"],
+        } as WeakRolesTodo);
+      }
+    }
+  }
+
+  // 4. Candidate cleanup todos
+  // Check if any candidate edges match missing link requirements
+  // Rule: If a confirmed edge already exists for the same relation, don't suggest candidate cleanup
+  for (const todo of todos) {
+    if (todo.type === "missing_link") {
+      const missingLinkTodo = todo as MissingLinkTodo;
+
+      // Check if confirmed edge already exists (relation equality)
+      const confirmedExists = checkRelationExists(
+        confirmedEdges,
+        missingLinkTodo.fromNodeRef,
+        missingLinkTodo.toNodeRef,
+        missingLinkTodo.suggestedEdgeTypes,
+        edgeVocabulary
+      );
+
+      if (confirmedExists) {
+        // Skip candidate cleanup if confirmed edge exists
+        continue;
+      }
+
+      // Find matching candidate edge
+      // Relation-Equality: same direction, same sourceRef/targetRef, canonical edgeType equal
+      const matchingCandidate = candidateEdges.find((candidate) => {
+        // Build keys for comparison
+        const candidateFromKey = `${
+          "sectionHeading" in candidate.source ? candidate.source.file : candidate.source.file
+        }:${"sectionHeading" in candidate.source ? candidate.source.sectionHeading || "" : ""}`;
+        const candidateToKey = `${candidate.target.file}:${candidate.target.heading || ""}`;
+
+        const requiredFromKey = `${missingLinkTodo.fromNodeRef.file}:${missingLinkTodo.fromNodeRef.heading || ""}`;
+        const requiredToKey = `${missingLinkTodo.toNodeRef.file}:${missingLinkTodo.toNodeRef.heading || ""}`;
+
+        // Check direction and node refs match
+        if (candidateFromKey !== requiredFromKey || candidateToKey !== requiredToKey) {
+          return false;
+        }
+
+        // Check canonical edge type match (internally canonical, but user can choose alias)
+        const candidateCanonical = edgeVocabulary
+          ? resolveCanonicalEdgeType(candidate.rawEdgeType, edgeVocabulary).canonical
+          : null;
+
+        if (!candidateCanonical) {
+          return false;
+        }
+
+        // Check if any suggested edge type matches (canonical comparison)
+        const matchesEdgeType = missingLinkTodo.suggestedEdgeTypes.some((suggested) => {
+          const suggestedCanonical = edgeVocabulary
+            ? resolveCanonicalEdgeType(suggested, edgeVocabulary).canonical
+            : null;
+          // Match if canonical types are equal
+          return candidateCanonical === suggestedCanonical || candidateCanonical === suggested;
+        });
+
+        return matchesEdgeType;
+      });
+
+      if (matchingCandidate) {
+        todos.push({
+          type: "candidate_cleanup",
+          id: `candidate_cleanup_${match.templateName}_${missingLinkTodo.fromSlotId}_${missingLinkTodo.toSlotId}`,
+          description: `Candidate edge matches missing link requirement for "${match.templateName}"`,
+          priority: "medium",
+          candidateEdge: {
+            rawEdgeType: matchingCandidate.rawEdgeType,
+            from: "sectionHeading" in matchingCandidate.source
+              ? { file: matchingCandidate.source.file, heading: matchingCandidate.source.sectionHeading }
+              : { file: matchingCandidate.source.file, heading: null },
+            to: matchingCandidate.target,
+            evidence: matchingCandidate.evidence,
+          },
+          neededFor: {
+            matchName: match.templateName,
+            linkFromSlot: missingLinkTodo.fromSlotId,
+            linkToSlot: missingLinkTodo.toSlotId,
+          },
+          actions: ["promote_candidate", "resolve_candidate"],
+        } as CandidateCleanupTodo);
+      }
+    }
+  }
+
+  return todos;
+}
+
+/**
+ * Check if a relation already exists in confirmed edges (relation equality).
+ */
+function checkRelationExists(
+  confirmedEdges: IndexedEdge[],
+  fromRef: { file: string; heading: string | null },
+  toRef: { file: string; heading: string | null },
+  suggestedEdgeTypes: string[],
+  edgeVocabulary: EdgeVocabulary | null
+): boolean {
+  const fromKey = `${fromRef.file}:${fromRef.heading || ""}`;
+  const toKey = `${toRef.file}:${toRef.heading || ""}`;
+
+  for (const edge of confirmedEdges) {
+    // Check direction and node refs
+    const edgeFromKey = `${
+      "sectionHeading" in edge.source ? edge.source.file : edge.source.file
+    }:${"sectionHeading" in edge.source ? edge.source.sectionHeading || "" : ""}`;
+    const edgeToKey = `${edge.target.file}:${edge.target.heading || ""}`;
+
+    if (edgeFromKey !== fromKey || edgeToKey !== toKey) {
+      continue;
+    }
+
+    // Check canonical edge type match
+    const edgeCanonical = edgeVocabulary
+      ? resolveCanonicalEdgeType(edge.rawEdgeType, edgeVocabulary).canonical
+      : null;
+
+    if (!edgeCanonical) {
+      continue;
+    }
+
+    // Check if matches any suggested type (canonical comparison)
+    const matches = suggestedEdgeTypes.some((suggested) => {
+      const suggestedCanonical = edgeVocabulary
+        ? resolveCanonicalEdgeType(suggested, edgeVocabulary).canonical
+        : null;
+      return edgeCanonical === suggestedCanonical || edgeCanonical === suggested;
+    });
+
+    if (matches) {
+      return true;
+    }
+  }
+
+  return false;
+}
+
+/**
+ * Generate todos from Chain Inspector findings.
+ */
+export function generateFindingsTodos(
+  findings: Finding[],
+  allEdges: IndexedEdge[],
+  context: { file: string; heading: string | null },
+  chainRoles: ChainRolesConfig | null,
+  edgeVocabulary: EdgeVocabulary | null
+): WorkbenchTodoUnion[] {
+  const todos: WorkbenchTodoUnion[] = [];
+
+  for (const finding of findings) {
+    switch (finding.code) {
+      case "dangling_target": {
+        // Find edge with dangling target
+        const danglingEdges = allEdges.filter((e) => {
+          // Check if edge targets a non-existent file
+          // The finding evidence points to the source section
+          const sourceMatches =
+            "sectionHeading" in e.source
+              ? e.source.sectionHeading === finding.evidence?.sectionHeading &&
+                e.source.file === finding.evidence?.file
+              : e.source.file === finding.evidence?.file;
+          return sourceMatches;
+        });
+
+        for (const edge of danglingEdges) {
+          todos.push({
+            type: "dangling_target",
+            id: `dangling_target_${edge.target.file}_${Date.now()}`,
+            description: finding.message,
+            priority: finding.severity === "error" ? "high" : "medium",
+            targetFile: edge.target.file,
+            targetHeading: edge.target.heading,
+            sourceEdge: {
+              file: "sectionHeading" in edge.source ? edge.source.file : edge.source.file,
+              heading: "sectionHeading" in edge.source ? edge.source.sectionHeading || null : null,
+            },
+            actions: ["create_missing_note", "retarget_link"],
+          } as DanglingTargetTodo);
+        }
+        break;
+      }
+
+      case "dangling_target_heading": {
+        todos.push({
+          type: "dangling_target_heading",
+          id: `dangling_target_heading_${finding.evidence?.file || ""}_${finding.evidence?.sectionHeading || ""}_${Date.now()}`,
+          description: finding.message,
+          priority: finding.severity === "warn" ? "medium" : "low",
+          targetFile: finding.evidence?.file || "",
+          targetHeading: finding.evidence?.sectionHeading || null,
+          actions: ["create_missing_heading", "retarget_to_existing_heading"],
+        } as DanglingTargetHeadingTodo);
+        break;
+      }
+
+      case "only_candidates": {
+        // Find all candidate edges in section
+        const candidateEdges = allEdges.filter(
+          (e) =>
+            e.scope === "candidate" &&
+            ("sectionHeading" in e.source
+              ? e.source.sectionHeading === context.heading && e.source.file === context.file
+              : false)
+        );
+
+        if (candidateEdges.length > 0) {
+          todos.push({
+            type: "only_candidates",
+            id: `only_candidates_${context.file}_${context.heading || ""}`,
+            description: finding.message,
+            priority: "medium",
+            candidateEdges: candidateEdges.map((e) => ({
+              rawEdgeType: e.rawEdgeType,
+              from: "sectionHeading" in e.source
+                ? { file: e.source.file, heading: e.source.sectionHeading || null }
+                : { file: e.source.file, heading: null },
+              to: e.target,
+            })),
+            actions: ["promote_all_candidates", "create_explicit_edges"],
+          } as OnlyCandidatesTodo);
+        }
+        break;
+      }
+
+      case "missing_edges": {
+        todos.push({
+          type: "missing_edges",
+          id: `missing_edges_${context.file}_${context.heading || ""}`,
+          description: finding.message,
+          priority: "medium",
+          section: {
+            file: context.file,
+            heading: context.heading,
+          },
+          actions: ["add_edges_to_section"],
+        } as MissingEdgesTodo);
+        break;
+      }
+
+      case "no_causal_roles": {
+        // Find edges without causal roles in the section
+        const nonCausalEdges = allEdges.filter(
+          (e) =>
+            e.scope === "section" &&
+            ("sectionHeading" in e.source
+              ? e.source.sectionHeading === context.heading && e.source.file === context.file
+              : false)
+        );
+
+        if (nonCausalEdges.length > 0 && chainRoles) {
+          // Resolve roles for each edge
+          const edgesWithRoles = nonCausalEdges.map((e) => {
+            let currentRole: string | null = null;
+
+            // Try to find role via chain_roles
+            if (edgeVocabulary) {
+              const { canonical } = resolveCanonicalEdgeType(e.rawEdgeType, edgeVocabulary);
+              for (const [roleName, role] of Object.entries(chainRoles.roles || {})) {
+                if (role.edge_types.includes(canonical || e.rawEdgeType)) {
+                  currentRole = roleName;
+                  break;
+                }
+              }
+            }
+
+            return {
+              rawEdgeType: e.rawEdgeType,
+              from: "sectionHeading" in e.source
+                ? { file: e.source.file, heading: e.source.sectionHeading || null }
+                : { file: e.source.file, heading: null },
+              to: e.target,
+              currentRole,
+              suggestedRoles: ["causal", "influences", "enables_constraints"],
+            };
+          });
+
+          todos.push({
+            type: "no_causal_roles",
+            id: `no_causal_roles_${context.file}_${context.heading || ""}`,
+            description: finding.message,
+            priority: "medium",
+            edges: edgesWithRoles,
+            actions: ["change_edge_type"],
+          } as NoCausalRolesTodo);
+        }
+        break;
+      }
+
+      case "one_sided_connectivity": {
+        // Informational only
+        todos.push({
+          type: "one_sided_connectivity",
+          id: `one_sided_connectivity_${context.file}_${context.heading || ""}`,
+          description: finding.message,
+          priority: "low",
+          section: {
+            file: context.file,
+            heading: context.heading,
+          },
+          actions: [],
+        } as OneSidedConnectivityTodo);
+        break;
+      }
+
+      // Skip template-based findings (they are handled by generateTodos)
+      case "missing_slot_trigger":
+      case "missing_slot_transformation":
+      case "missing_slot_outcome":
+      case "missing_link_constraints":
+      case "weak_chain_roles":
+        // These are template-based and handled separately
+        break;
+
+      default:
+        // Unknown finding code - skip
+        break;
+    }
+  }
+
+  return todos;
+}

src/workbench/types.ts

@@ -0,0 +1,233 @@
+/**
+ * Chain Workbench Types
+ */
+
+import type { TemplateMatch } from "../analysis/chainInspector";
+
+/**
+ * Status of a template match.
+ */
+export type MatchStatus = "complete" | "near_complete" | "partial" | "weak";
+
+/**
+ * Workbench Match extends TemplateMatch with status and todos.
+ */
+export interface WorkbenchMatch extends TemplateMatch {
+  status: MatchStatus;
+  slotsFilled: number;
+  slotsTotal: number;
+  effectiveRequiredLinks: boolean;
+  todos: WorkbenchTodo[];
+}
+
+/**
+ * Todo types for workbench.
+ */
+export type TodoType =
+  | "missing_slot"
+  | "missing_link"
+  | "weak_roles"
+  | "candidate_cleanup"
+  | "create_candidates_zone"
+  | "create_note_links_zone"
+  | "dangling_target"
+  | "dangling_target_heading"
+  | "only_candidates"
+  | "missing_edges"
+  | "no_causal_roles"
+  | "one_sided_connectivity";
+
+/**
+ * Base todo interface.
+ */
+export interface WorkbenchTodo {
+  type: TodoType;
+  id: string; // Unique ID for this todo
+  description: string;
+  priority: "high" | "medium" | "low";
+}
+
+/**
+ * Missing slot todo.
+ */
+export interface MissingSlotTodo extends WorkbenchTodo {
+  type: "missing_slot";
+  slotId: string;
+  allowedNodeTypes: string[];
+  actions: Array<"link_existing" | "create_note_via_interview">;
+}
+
+/**
+ * Missing link todo.
+ */
+export interface MissingLinkTodo extends WorkbenchTodo {
+  type: "missing_link";
+  fromSlotId: string;
+  toSlotId: string;
+  fromNodeRef: {
+    file: string;
+    heading: string | null;
+    noteType: string;
+  };
+  toNodeRef: {
+    file: string;
+    heading: string | null;
+    noteType: string;
+  };
+  allowedEdgeRoles: string[];
+  suggestedEdgeTypes: string[]; // Canonical types from chain_roles
+  actions: Array<"insert_edge_forward" | "insert_edge_inverse" | "choose_target_anchor">;
+}
+
+/**
+ * Weak roles todo.
+ */
+export interface WeakRolesTodo extends WorkbenchTodo {
+  type: "weak_roles";
+  edges: Array<{
+    rawEdgeType: string;
+    from: { file: string; heading: string | null };
+    to: { file: string; heading: string | null };
+    currentRole: string | null;
+    suggestedRoles: string[]; // causal, enables_constraints
+  }>;
+  actions: Array<"change_edge_type">;
+}
+
+/**
+ * Candidate cleanup todo.
+ */
+export interface CandidateCleanupTodo extends WorkbenchTodo {
+  type: "candidate_cleanup";
+  candidateEdge: {
+    rawEdgeType: string;
+    from: { file: string; heading: string | null };
+    to: { file: string; heading: string | null };
+    evidence: {
+      file: string;
+      sectionHeading: string | null;
+      lineRange?: { start: number; end: number };
+    };
+  };
+  neededFor: {
+    matchName: string;
+    linkFromSlot: string;
+    linkToSlot: string;
+  };
+  actions: Array<"promote_candidate" | "resolve_candidate">;
+}
+
+/**
+ * Create zone todo.
+ */
+export interface CreateZoneTodo extends WorkbenchTodo {
+  type: "create_candidates_zone" | "create_note_links_zone";
+  zoneType: "candidates" | "note_links";
+  file: string;
+}
+
+/**
+ * Dangling target todo (from findings).
+ */
+export interface DanglingTargetTodo extends WorkbenchTodo {
+  type: "dangling_target";
+  targetFile: string;
+  targetHeading: string | null;
+  sourceEdge: {
+    file: string;
+    heading: string | null;
+  };
+  actions: Array<"create_missing_note" | "retarget_link">;
+}
+
+/**
+ * Dangling target heading todo (from findings).
+ */
+export interface DanglingTargetHeadingTodo extends WorkbenchTodo {
+  type: "dangling_target_heading";
+  targetFile: string;
+  targetHeading: string | null;
+  actions: Array<"create_missing_heading" | "retarget_to_existing_heading">;
+}
+
+/**
+ * Only candidates todo (from findings).
+ */
+export interface OnlyCandidatesTodo extends WorkbenchTodo {
+  type: "only_candidates";
+  candidateEdges: Array<{
+    rawEdgeType: string;
+    from: { file: string; heading: string | null };
+    to: { file: string; heading: string | null };
+  }>;
+  actions: Array<"promote_all_candidates" | "create_explicit_edges">;
+}
+
+/**
+ * Missing edges todo (from findings).
+ */
+export interface MissingEdgesTodo extends WorkbenchTodo {
+  type: "missing_edges";
+  section: {
+    file: string;
+    heading: string | null;
+  };
+  actions: Array<"add_edges_to_section">;
+}
+
+/**
+ * No causal roles todo (from findings).
+ */
+export interface NoCausalRolesTodo extends WorkbenchTodo {
+  type: "no_causal_roles";
+  edges: Array<{
+    rawEdgeType: string;
+    from: { file: string; heading: string | null };
+    to: { file: string; heading: string | null };
+    currentRole: string | null;
+    suggestedRoles: string[];
+  }>;
+  actions: Array<"change_edge_type">;
+}
+
+/**
+ * One-sided connectivity todo (from findings, informational only).
+ */
+export interface OneSidedConnectivityTodo extends WorkbenchTodo {
+  type: "one_sided_connectivity";
+  section: {
+    file: string;
+    heading: string | null;
+  };
+  actions: []; // Informational only
+}
+
+/**
+ * Union type for all todos.
+ */
+export type WorkbenchTodoUnion =
+  | MissingSlotTodo
+  | MissingLinkTodo
+  | WeakRolesTodo
+  | CandidateCleanupTodo
+  | CreateZoneTodo
+  | DanglingTargetTodo
+  | DanglingTargetHeadingTodo
+  | OnlyCandidatesTodo
+  | MissingEdgesTodo
+  | NoCausalRolesTodo
+  | OneSidedConnectivityTodo;
+
+/**
+ * Workbench model containing all matches and their todos.
+ */
+export interface WorkbenchModel {
+  context: {
+    file: string;
+    heading: string | null;
+    zoneKind: string;
+  };
+  matches: WorkbenchMatch[];
+  globalTodos?: WorkbenchTodoUnion[]; // Todos from findings (not template-based)
+  timestamp: number;
+}

src/workbench/vaultTriageScan.ts

@@ -0,0 +1,245 @@
+/**
+ * Vault Triage Scan - Scan vault for chain gaps and generate backlog.
+ */
+
+import type { App, TFile } from "obsidian";
+import type { ChainRolesConfig, ChainTemplatesConfig } from "../dictionary/types";
+import type { MindnetSettings } from "../settings";
+import type { EdgeVocabulary } from "../vocab/types";
+import { inspectChains } from "../analysis/chainInspector";
+import { buildNoteIndex } from "../analysis/graphIndex";
+import type { SectionContext } from "../analysis/sectionContext";
+import { splitIntoSections } from "../mapping/sectionParser";
+import { buildWorkbenchModel } from "./workbenchBuilder";
+import type { WorkbenchMatch } from "./types";
+
+export interface ScanItem {
+  file: string;
+  heading: string | null;
+  matches: Array<{
+    templateName: string;
+    status: string;
+    score: number;
+    slotsFilled: number;
+    slotsTotal: number;
+    satisfiedLinks: number;
+    requiredLinks: number;
+    todosCount: number;
+  }>;
+  gapCounts: {
+    missingSlots: number;
+    missingLinks: number;
+    weakRoles: number;
+    candidateCleanup: number;
+  };
+  status: "near_complete" | "partial" | "weak" | "deprioritized";
+}
+
+export interface ScanState {
+  items: ScanItem[];
+  timestamp: number;
+  progress: {
+    current: number;
+    total: number;
+    currentFile: string | null;
+  };
+  completed: boolean;
+}
+
+/**
+ * Scan vault for chain gaps.
+ */
+export async function scanVaultForChainGaps(
+  app: App,
+  chainRoles: ChainRolesConfig | null,
+  chainTemplates: ChainTemplatesConfig | null,
+  edgeVocabulary: EdgeVocabulary | null,
+  settings: MindnetSettings,
+  onProgress?: (progress: { current: number; total: number; currentFile: string | null }) => void,
+  shouldCancel?: () => boolean
+): Promise<ScanItem[]> {
+  const items: ScanItem[] = [];
+  
+  // Get all markdown files
+  const allFiles = app.vault.getMarkdownFiles();
+  const total = allFiles.length;
+  
+  for (let i = 0; i < allFiles.length; i++) {
+    const file = allFiles[i];
+    if (!file) continue;
+    
+    // Check if should cancel
+    if (shouldCancel && shouldCancel()) {
+      break;
+    }
+    
+    // Report progress
+    if (onProgress) {
+      onProgress({
+        current: i + 1,
+        total,
+        currentFile: file.path,
+      });
+    }
+    
+    try {
+      // Read file content
+      const content = await app.vault.read(file);
+      
+      // Split into sections
+      const sections = splitIntoSections(content);
+      
+      // Process each section
+      for (let sectionIndex = 0; sectionIndex < sections.length; sectionIndex++) {
+        const section = sections[sectionIndex];
+        if (!section) continue;
+        
+        // Skip special zones
+        if (section.heading === "Kandidaten" || section.heading === "Note-Verbindungen") {
+          continue;
+        }
+        
+        // Create context directly from section
+        const context: SectionContext = {
+          file: file.path,
+          heading: section.heading,
+          zoneKind: section.heading === null 
+            ? "root" 
+            : section.heading === "Note-Verbindungen" 
+              ? "note_links" 
+              : section.heading === "Kandidaten" 
+                ? "candidates" 
+                : "content",
+          sectionIndex: sectionIndex,
+        };
+        
+        // Build inspector options
+        const inspectorOptions = {
+          includeNoteLinks: true,
+          includeCandidates: settings.chainInspectorIncludeCandidates,
+          maxDepth: 3,
+          direction: "both" as const,
+          maxTemplateMatches: undefined, // No limit
+        };
+        
+        // Prepare templates source info
+        const templatesSourceInfo = {
+          path: settings.chainTemplatesPath || "",
+          status: "loaded" as const,
+          loadedAt: Date.now(),
+          templateCount: chainTemplates?.templates?.length || 0,
+        };
+        
+        // Inspect chains
+        const report = await inspectChains(
+          app,
+          context,
+          inspectorOptions,
+          chainRoles,
+          settings.edgeVocabularyPath,
+          chainTemplates,
+          templatesSourceInfo,
+          settings.templateMatchingProfile
+        );
+        
+        // Build edges index
+        const { edges: allEdges } = await buildNoteIndex(app, file);
+        
+        // Build workbench model
+        const workbenchModel = await buildWorkbenchModel(
+          app,
+          report,
+          chainTemplates,
+          chainRoles,
+          edgeVocabulary,
+          allEdges
+        );
+        
+        // Skip if no matches
+        if (workbenchModel.matches.length === 0) {
+          continue;
+        }
+        
+        // Calculate gap counts
+        const gapCounts = {
+          missingSlots: 0,
+          missingLinks: 0,
+          weakRoles: 0,
+          candidateCleanup: 0,
+        };
+        
+        for (const match of workbenchModel.matches) {
+          for (const todo of match.todos) {
+            if (todo.type === "missing_slot") gapCounts.missingSlots++;
+            else if (todo.type === "missing_link") gapCounts.missingLinks++;
+            else if (todo.type === "weak_roles") gapCounts.weakRoles++;
+            else if (todo.type === "candidate_cleanup") gapCounts.candidateCleanup++;
+          }
+        }
+        
+        // Determine overall status (prioritize near_complete)
+        let overallStatus: "near_complete" | "partial" | "weak" = "partial";
+        const hasNearComplete = workbenchModel.matches.some((m) => m.status === "near_complete");
+        const hasWeak = workbenchModel.matches.some((m) => m.status === "weak");
+        
+        if (hasNearComplete) {
+          overallStatus = "near_complete";
+        } else if (hasWeak) {
+          overallStatus = "weak";
+        }
+        
+        // Add scan item
+        items.push({
+          file: file.path,
+          heading: section.heading,
+          matches: workbenchModel.matches.map((m) => ({
+            templateName: m.templateName,
+            status: m.status,
+            score: m.score,
+            slotsFilled: m.slotsFilled,
+            slotsTotal: m.slotsTotal,
+            satisfiedLinks: m.satisfiedLinks,
+            requiredLinks: m.requiredLinks,
+            todosCount: m.todos.length,
+          })),
+          gapCounts,
+          status: overallStatus,
+        });
+      }
+    } catch (e) {
+      console.error(`[Vault Triage Scan] Error processing ${file.path}:`, e);
+      // Continue with next file
+    }
+  }
+  
+  return items;
+}
+
+/**
+ * Save scan state to plugin data store.
+ */
+export async function saveScanState(
+  app: App,
+  state: ScanState,
+  pluginInstance: any
+): Promise<void> {
+  if (pluginInstance && pluginInstance.loadData && pluginInstance.saveData) {
+    await pluginInstance.saveData({
+      vaultTriageScanState: state,
+    });
+  }
+}
+
+/**
+ * Load scan state from plugin data store.
+ */
+export async function loadScanState(
+  app: App,
+  pluginInstance: any
+): Promise<ScanState | null> {
+  if (pluginInstance && pluginInstance.loadData) {
+    const data = await pluginInstance.loadData();
+    return data?.vaultTriageScanState || null;
+  }
+  return null;
+}

src/workbench/workbenchBuilder.ts

@@ -0,0 +1,108 @@
+/**
+ * Build workbench model from chain inspector report.
+ */
+
+import type { App } from "obsidian";
+import type { ChainInspectorReport } from "../analysis/chainInspector";
+import type { ChainRolesConfig, ChainTemplatesConfig } from "../dictionary/types";
+import type { EdgeVocabulary } from "../vocab/types";
+import type { IndexedEdge } from "../analysis/graphIndex";
+import type { WorkbenchModel, WorkbenchMatch, WorkbenchTodoUnion } from "./types";
+import { calculateMatchStatus, calculateSlotsStats, hasWeakRoles, getEffectiveRequiredLinks } from "./statusCalculator";
+import { generateTodos, generateFindingsTodos } from "./todoGenerator";
+
+/**
+ * Build workbench model from chain inspector report.
+ */
+export async function buildWorkbenchModel(
+  app: App,
+  report: ChainInspectorReport,
+  chainTemplates: ChainTemplatesConfig | null,
+  chainRoles: ChainRolesConfig | null,
+  edgeVocabulary: EdgeVocabulary | null,
+  allEdges: IndexedEdge[]
+): Promise<WorkbenchModel> {
+  const matches: WorkbenchMatch[] = [];
+
+  if (!report.templateMatches || !chainTemplates) {
+    return {
+      context: report.context,
+      matches: [],
+      timestamp: Date.now(),
+    };
+  }
+
+  // Get candidate edges from current note
+  // Also check for confirmed edges that would make candidates "not needed"
+  const candidateEdges = allEdges.filter((e) => e.scope === "candidate");
+  const confirmedEdges = allEdges.filter((e) => e.scope !== "candidate");
+
+  // Get profile config for required_links resolution
+  const profileConfig = report.templateMatchingProfileUsed?.profileConfig;
+  const profileRequiredLinks = profileConfig?.required_links;
+
+  for (const match of report.templateMatches) {
+    // Find template
+    const template = chainTemplates.templates.find((t) => t.name === match.templateName);
+    if (!template) continue;
+
+    // Calculate slots stats
+    const slotsStats = calculateSlotsStats(match);
+
+    // Check for weak roles
+    const matchHasWeakRoles = hasWeakRoles(match);
+
+    // Calculate status
+    const status = calculateMatchStatus(match, matchHasWeakRoles);
+
+    // Get effective required_links
+    const effectiveRequiredLinks = getEffectiveRequiredLinks(
+      match,
+      profileRequiredLinks,
+      template.matching?.required_links,
+      chainTemplates.defaults?.matching?.required_links
+    );
+
+    // Generate todos
+    const todos = await generateTodos(
+      app,
+      match,
+      template,
+      chainRoles,
+      edgeVocabulary,
+      allEdges,
+      candidateEdges,
+      confirmedEdges,
+      report.context
+    );
+
+    matches.push({
+      ...match,
+      status,
+      slotsFilled: slotsStats.filled,
+      slotsTotal: slotsStats.total,
+      effectiveRequiredLinks,
+      todos,
+    });
+  }
+
+  // Generate todos from findings
+  const globalTodos: WorkbenchTodoUnion[] = [];
+  if (report.findings && report.findings.length > 0) {
+    const findingsTodos = generateFindingsTodos(
+      report.findings,
+      allEdges,
+      report.context,
+      chainRoles,
+      edgeVocabulary
+    );
+    globalTodos.push(...findingsTodos);
+  }
+
+  return {
+    context: report.context,
+    matches,
+    globalTodos: globalTodos.length > 0 ? globalTodos : undefined,
+    timestamp: Date.now(),
+  };
+}

src/workbench/writerActions.ts

@@ -0,0 +1,780 @@
+/**
+ * Writer actions for workbench todos.
+ */
+
+import { Modal, Setting, TFile, Notice } from "obsidian";
+import type { App, Editor } from "obsidian";
+import type { MissingLinkTodo, CandidateCleanupTodo, MissingSlotTodo } from "./types";
+import { detectZone, findSection } from "./zoneDetector";
+import { splitIntoSections } from "../mapping/sectionParser";
+import { EntityPickerModal } from "../ui/EntityPickerModal";
+import { NoteIndex } from "../entityPicker/noteIndex";
+import { EdgeTypeChooserModal } from "../ui/EdgeTypeChooserModal";
+import type { Vocabulary } from "../vocab/Vocabulary";
+import type { EdgeVocabulary } from "../vocab/types";
+import type { MindnetSettings } from "../settings";
+import { extractExistingMappings } from "../mapping/mappingExtractor";
+import { buildMappingBlock, insertMappingBlock } from "../mapping/mappingBuilder";
+
+/**
+ * Insert edge forward (from source to target).
+ */
+export async function insertEdgeForward(
+  app: App,
+  editor: Editor,
+  file: TFile,
+  todo: MissingLinkTodo,
+  vocabulary: Vocabulary,
+  edgeVocabulary: EdgeVocabulary,
+  settings: MindnetSettings,
+  graphSchema: any = null,
+  targetZone: "section" | "note_links" | "candidates" = "section"
+): Promise<void> {
+  console.log("[insertEdgeForward] ===== STARTING =====");
+  console.log("[insertEdgeForward] targetZone:", targetZone);
+  console.log("[insertEdgeForward] file:", file.path);
+  console.log("[insertEdgeForward] todo type:", todo.type);
+  console.log("[insertEdgeForward] Todo:", todo);
+  console.log("[insertEdgeForward] Suggested edge types:", todo.suggestedEdgeTypes);
+  
+  // Let user choose edge type (direction is always "forward" for insert_edge_forward)
+  console.log("[insertEdgeForward] Opening edge type chooser...");
+  const edgeType = await chooseEdgeType(
+    app,
+    edgeVocabulary,
+    todo.suggestedEdgeTypes,
+    todo.fromNodeRef.noteType,
+    todo.toNodeRef.noteType,
+    graphSchema,
+    "forward" // insert_edge_forward is always forward direction
+  );
+  console.log("[insertEdgeForward] Selected edge type:", edgeType);
+  
+  if (!edgeType) {
+    console.log("[insertEdgeForward] User cancelled edge type selection");
+    return; // User cancelled
+  }
+
+  // Build target link (extract basename from file path)
+  const targetBasename = todo.toNodeRef.file.replace(/\.md$/, "").split("/").pop() || todo.toNodeRef.file;
+  const targetLink = todo.toNodeRef.heading
+    ? `${targetBasename}#${todo.toNodeRef.heading}`
+    : targetBasename;
+
+  console.log("[insertEdgeForward] Target link:", targetLink);
+  console.log("[insertEdgeForward] Inserting into zone:", targetZone);
+
+  // Determine where to insert
+  if (targetZone === "note_links") {
+    // Insert in Note-Verbindungen zone
+    console.log("[insertEdgeForward] Inserting into note_links zone");
+    await insertEdgeInZone(app, editor, file, "note_links", edgeType, targetLink, settings);
+  } else if (targetZone === "candidates") {
+    // Insert in Kandidaten zone
+    console.log("[insertEdgeForward] Inserting into candidates zone");
+    await insertEdgeInZone(app, editor, file, "candidates", edgeType, targetLink, settings);
+  } else {
+    // Insert in source section - need to select section if multiple exist
+    // IMPORTANT: Use source note (fromNodeRef.file), not current note!
+    // Try to find source file - it might be full path, basename, or basename without .md
+    let sourceFile: TFile | null = null;
+    const fileRef = todo.fromNodeRef.file;
+    
+    // Try different formats
+    const possiblePaths = [
+      fileRef, // Full path as-is
+      fileRef + ".md", // Add .md extension
+      fileRef.replace(/\.md$/, ""), // Remove .md if present
+      fileRef.replace(/\.md$/, "") + ".md", // Ensure .md
+    ];
+    
+    // Also try with current file's directory if it's a relative path
+    const currentDir = file.path.split("/").slice(0, -1).join("/");
+    if (currentDir) {
+      possiblePaths.push(
+        `${currentDir}/${fileRef}`,
+        `${currentDir}/${fileRef}.md`,
+        `${currentDir}/${fileRef.replace(/\.md$/, "")}.md`
+      );
+    }
+    
+    console.log("[insertEdgeForward] Trying to find source file, fileRef:", fileRef);
+    console.log("[insertEdgeForward] Possible paths:", possiblePaths);
+    
+    for (const path of possiblePaths) {
+      const found = app.vault.getAbstractFileByPath(path);
+      if (found && found instanceof TFile) {
+        sourceFile = found;
+        console.log("[insertEdgeForward] Found source file at path:", path);
+        break;
+      }
+    }
+    
+    // If still not found, try resolving as wikilink (like templateMatching does)
+    if (!sourceFile) {
+      const basename = fileRef.replace(/\.md$/, "").split("/").pop() || fileRef;
+      console.log("[insertEdgeForward] Trying to resolve as wikilink, basename:", basename);
+      const resolved = app.metadataCache.getFirstLinkpathDest(basename, file.path);
+      if (resolved) {
+        sourceFile = resolved;
+        console.log("[insertEdgeForward] Found source file via wikilink resolution:", sourceFile.path);
+      }
+    }
+    
+    // If still not found, try searching by basename in all files
+    if (!sourceFile) {
+      const basename = fileRef.replace(/\.md$/, "").split("/").pop() || fileRef;
+      console.log("[insertEdgeForward] Searching by basename in all files:", basename);
+      const allFiles = app.vault.getMarkdownFiles();
+      sourceFile = allFiles.find((f) => {
+        const fBasename = f.basename;
+        const fPath = f.path;
+        return fBasename === basename || fPath.endsWith(`/${basename}.md`) || fPath === `${basename}.md`;
+      }) || null;
+      
+      if (sourceFile) {
+        console.log("[insertEdgeForward] Found source file by basename:", sourceFile.path);
+      }
+    }
+    
+    if (!sourceFile) {
+      console.error("[insertEdgeForward] Source file not found. fileRef:", fileRef, "tried paths:", possiblePaths);
+      new Notice(`Source file not found: ${fileRef}`);
+      return;
+    }
+    
+    console.log("[insertEdgeForward] Inserting into section, source file:", sourceFile.path, "preferred heading:", todo.fromNodeRef.heading);
+    const sourceSection = await selectSectionForEdge(
+      app,
+      sourceFile,
+      todo.fromNodeRef.heading
+    );
+    console.log("[insertEdgeForward] Selected section:", sourceSection);
+    
+    if (!sourceSection) {
+      console.log("[insertEdgeForward] User cancelled section selection");
+      return; // User cancelled
+    }
+
+    // Get editor for source file (or create one)
+    let sourceEditor = editor;
+    if (sourceFile.path !== file.path) {
+      // Open source file in editor temporarily
+      await app.workspace.openLinkText(sourceFile.path, "", false);
+      const activeEditor = app.workspace.activeEditor?.editor;
+      if (!activeEditor) {
+        console.error("[insertEdgeForward] Could not get editor for source file");
+        return;
+      }
+      sourceEditor = activeEditor;
+    }
+
+    console.log("[insertEdgeForward] Inserting edge into section");
+    await insertEdgeInSection(
+      app,
+      sourceEditor,
+      sourceFile,
+      sourceSection,
+      edgeType,
+      targetLink,
+      settings
+    );
+    console.log("[insertEdgeForward] Edge insertion completed");
+  }
+}
+
+/**
+ * Insert edge in zone (Kandidaten or Note-Verbindungen).
+ */
+async function insertEdgeInZone(
+  app: App,
+  editor: Editor,
+  file: TFile,
+  zoneType: "candidates" | "note_links",
+  edgeType: string,
+  targetLink: string,
+  settings: MindnetSettings
+): Promise<void> {
+  const zone = await detectZone(app, file, zoneType);
+
+  const wrapperCalloutType = settings.mappingWrapperCalloutType || "abstract";
+  const wrapperTitle = settings.mappingWrapperTitle || "🕸️ Semantic Mapping";
+  const foldMarker = settings.mappingWrapperFolded ? "-" : "+";
+
+  if (!zone.exists) {
+    // Create zone
+    const content = editor.getValue();
+    const newZone = `\n\n## ${zoneType === "candidates" ? "Kandidaten" : "Note-Verbindungen"}\n\n> [!${wrapperCalloutType}]${foldMarker} ${wrapperTitle}\n>> [!edge] ${edgeType}\n>> [[${targetLink}]]\n`;
+    const newContent = content + newZone;
+    editor.setValue(newContent);
+    return;
+  }
+
+  // Insert in existing zone
+  const content = editor.getValue();
+  const lines = content.split(/\r?\n/);
+
+  // Find insertion point (end of zone, before next heading)
+  let insertLine = zone.endLine - 1;
+
+  // Check if zone has a wrapper callout using settings
+  const zoneContent = zone.content;
+  const hasWrapper = zoneContent.includes(`> [!${wrapperCalloutType}]`) && 
+                     zoneContent.includes(wrapperTitle);
+
+  if (hasWrapper) {
+    // Insert inside wrapper - find the end of the wrapper block
+    const wrapperEndLine = findWrapperBlockEnd(lines, zone.startLine, wrapperCalloutType, wrapperTitle);
+    if (wrapperEndLine !== null) {
+      insertLine = wrapperEndLine - 1;
+    }
+    const newEdge = `>> [!edge] ${edgeType}\n>> [[${targetLink}]]\n`;
+    lines.splice(insertLine, 0, ...newEdge.split("\n"));
+  } else {
+    // Create wrapper and insert edge
+    const wrapper = `\n> [!${wrapperCalloutType}]${foldMarker} ${wrapperTitle}\n>> [!edge] ${edgeType}\n>> [[${targetLink}]]\n`;
+    lines.splice(insertLine, 0, ...wrapper.split("\n"));
+  }
+
+  editor.setValue(lines.join("\n"));
+}
+
+/**
+ * Find the end line of a wrapper block.
+ */
+function findWrapperBlockEnd(
+  lines: string[],
+  startLine: number,
+  calloutType: string,
+  title: string
+): number | null {
+  const calloutTypeLower = calloutType.toLowerCase();
+  const titleLower = title.toLowerCase();
+  const calloutHeaderRegex = new RegExp(
+    `^\\s*>\\s*\\[!${calloutTypeLower.replace(/[.*+?^${}()|[\]\\]/g, "\\$&")}\\]\\s*[+-]?\\s*(.+)$`,
+    "i"
+  );
+
+  let inWrapper = false;
+  let quoteLevel = 0;
+
+  for (let i = startLine; i < lines.length; i++) {
+    const line = lines[i];
+    if (line === undefined) continue;
+
+    const trimmed = line.trim();
+    const match = line.match(calloutHeaderRegex);
+
+    if (match && match[1]) {
+      const headerTitle = match[1].trim().toLowerCase();
+      if (headerTitle.includes(titleLower) || titleLower.includes(headerTitle)) {
+        inWrapper = true;
+        quoteLevel = (line.match(/^\s*(>+)/)?.[1]?.length || 0);
+        continue;
+      }
+    }
+
+    if (inWrapper) {
+      if (trimmed.match(/^\^map-/)) {
+        return i + 1;
+      }
+
+      const currentQuoteLevel = (line.match(/^\s*(>+)/)?.[1]?.length || 0);
+      if (trimmed !== "" && currentQuoteLevel < quoteLevel) {
+        return i;
+      }
+
+      if (!line.startsWith(">") && trimmed.match(/^#{1,6}\s+/)) {
+        return i;
+      }
+    }
+  }
+
+  return inWrapper ? lines.length : null;
+}
+
+/**
+ * Select section for edge insertion (if multiple sections exist).
+ */
+async function selectSectionForEdge(
+  app: App,
+  file: TFile,
+  preferredHeading: string | null
+): Promise<{ startLine: number; endLine: number; content: string; heading: string | null } | null> {
+  console.log("[selectSectionForEdge] Starting, preferredHeading:", preferredHeading);
+  const content = await app.vault.read(file);
+  const sections = splitIntoSections(content);
+  console.log("[selectSectionForEdge] Found", sections.length, "sections");
+  console.log("[selectSectionForEdge] Section headings:", sections.map(s => s.heading));
+
+  // Filter out special zones
+  const contentSections = sections.filter(
+    (s) => s.heading !== "Kandidaten" && s.heading !== "Note-Verbindungen"
+  );
+  console.log("[selectSectionForEdge] Content sections after filtering:", contentSections.length);
+  console.log("[selectSectionForEdge] Content section headings:", contentSections.map(s => s.heading));
+
+  if (contentSections.length === 0) {
+    console.log("[selectSectionForEdge] No content sections found");
+    return null;
+  }
+
+  // If only one section, use it (no need to ask)
+  if (contentSections.length === 1) {
+    const section = contentSections[0];
+    if (!section) return null;
+    console.log("[selectSectionForEdge] Using single section:", section.heading || "(Root)");
+    return {
+      startLine: section.startLine,
+      endLine: section.endLine,
+      content: section.content,
+      heading: section.heading,
+    };
+  }
+
+  // Multiple sections - always show selection modal
+  // If preferred heading matches, highlight it or select it by default
+  // But still show the modal so user can confirm or choose differently
+  console.log("[selectSectionForEdge] Multiple sections found, showing selection modal");
+  console.log("[selectSectionForEdge] Preferred heading:", preferredHeading);
+  return new Promise((resolve) => {
+    let resolved = false;
+    const modal = new Modal(app);
+    modal.titleEl.textContent = "Select Section";
+    const description = preferredHeading 
+      ? `Which section should the edge be inserted into? (Preferred: "${preferredHeading}")`
+      : "Which section should the edge be inserted into?";
+    modal.contentEl.createEl("p", { text: description });
+
+    const doResolve = (value: { startLine: number; endLine: number; content: string; heading: string | null } | null) => {
+      if (!resolved) {
+        resolved = true;
+        resolve(value);
+      }
+    };
+
+    for (const section of contentSections) {
+      if (!section) continue;
+      const sectionName = section.heading || "(Root section)";
+      const isPreferred = preferredHeading && section.heading === preferredHeading;
+      const setting = new Setting(modal.contentEl);
+      
+      if (isPreferred) {
+        setting.setName(`⭐ ${sectionName} (preferred)`);
+        setting.setDesc(`Lines ${section.startLine + 1}-${section.endLine} - Recommended based on chain template`);
+      } else {
+        setting.setName(sectionName);
+        setting.setDesc(`Lines ${section.startLine + 1}-${section.endLine}`);
+      }
+      
+      setting.addButton((btn) => {
+        if (isPreferred) {
+          btn.setButtonText("Select (Recommended)");
+          btn.setCta(); // Highlight recommended option
+        } else {
+          btn.setButtonText("Select");
+        }
+        btn.onClick(() => {
+          console.log("[selectSectionForEdge] User selected section:", sectionName);
+          doResolve({
+            startLine: section.startLine,
+            endLine: section.endLine,
+            content: section.content,
+            heading: section.heading,
+          });
+          modal.close();
+        });
+      });
+    }
+
+    modal.onClose = () => {
+      console.log("[selectSectionForEdge] Modal closed, resolved:", resolved);
+      if (!resolved) {
+        console.log("[selectSectionForEdge] Resolving with null (user cancelled)");
+        doResolve(null);
+      }
+    };
+    modal.open();
+  });
+}
+
+/**
+ * Insert edge in section (section-scope).
+ */
+async function insertEdgeInSection(
+  app: App,
+  editor: Editor,
+  file: TFile,
+  section: { startLine: number; endLine: number; content: string },
+  edgeType: string,
+  targetLink: string,
+  settings: MindnetSettings
+): Promise<void> {
+  const content = editor.getValue();
+  const lines = content.split(/\r?\n/);
+
+  // Get wrapper settings
+  const wrapperCalloutType = settings.mappingWrapperCalloutType || "abstract";
+  const wrapperTitle = settings.mappingWrapperTitle || "🕸️ Semantic Mapping";
+  const wrapperFolded = settings.mappingWrapperFolded !== false;
+
+  // Extract existing mappings from section
+  const mappingState = extractExistingMappings(section.content, wrapperCalloutType, wrapperTitle);
+
+  // Check if section has semantic mapping block
+  const hasMappingBlock = mappingState.wrapperBlockStartLine !== null;
+
+  if (hasMappingBlock && mappingState.wrapperBlockStartLine !== null && mappingState.wrapperBlockEndLine !== null) {
+    console.log("[insertEdgeInSection] Inserting into existing mapping block");
+    // Insert edge into existing mapping block
+    const sectionLines = section.content.split(/\r?\n/);
+    const wrapperStart = mappingState.wrapperBlockStartLine;
+    const wrapperEnd = mappingState.wrapperBlockEndLine;
+    
+    // Find if edgeType group already exists in wrapper block
+    const wrapperBlockContent = sectionLines.slice(wrapperStart, wrapperEnd).join("\n");
+    console.log("[insertEdgeInSection] Wrapper block content length:", wrapperBlockContent.length);
+    
+    const edgeTypeGroupRegex = new RegExp(`(>>\\s*\\[!edge\\]\\s+${edgeType.replace(/[.*+?^${}()|[\]\\]/g, "\\$&")}[\\s\\S]*?)(?=\\n\\n|\\n>>\\s*\\[!edge\\]|\\n>\\s*\\^map-|$)`);
+    const edgeTypeMatch = wrapperBlockContent.match(edgeTypeGroupRegex);
+    console.log("[insertEdgeInSection] Edge type group match:", edgeTypeMatch ? "found" : "not found");
+    
+    if (edgeTypeMatch && edgeTypeMatch[1]) {
+      console.log("[insertEdgeInSection] Appending to existing edge type group");
+      // Edge type group exists - append to it
+      const newEdge = `>> [[${targetLink}]]\n`;
+      const updatedGroup = edgeTypeMatch[1].trimEnd() + "\n" + newEdge;
+      const updatedWrapperBlock = wrapperBlockContent.replace(edgeTypeMatch[0], updatedGroup);
+      
+      // Replace wrapper block in section
+      const beforeWrapper = sectionLines.slice(0, wrapperStart).join("\n");
+      const afterWrapper = sectionLines.slice(wrapperEnd).join("\n");
+      const newSectionContent = beforeWrapper + "\n" + updatedWrapperBlock + "\n" + afterWrapper;
+      
+      // Replace section in full content
+      const beforeSection = lines.slice(0, section.startLine).join("\n");
+      const afterSection = lines.slice(section.endLine).join("\n");
+      const newContent = beforeSection + "\n" + newSectionContent + "\n" + afterSection;
+      console.log("[insertEdgeInSection] Setting new content, length:", newContent.length);
+      editor.setValue(newContent);
+      console.log("[insertEdgeInSection] Content updated successfully");
+      return;
+    } else {
+      console.log("[insertEdgeInSection] Adding new edge type group");
+      // Edge type group doesn't exist - add new group before block-id marker or at end
+      const blockIdMatch = wrapperBlockContent.match(/\n>?\s*\^map-/);
+      const insertPos = blockIdMatch ? blockIdMatch.index || wrapperBlockContent.length : wrapperBlockContent.length;
+      console.log("[insertEdgeInSection] Insert position:", insertPos);
+      
+      const newEdgeGroup = `\n>> [!edge] ${edgeType}\n>> [[${targetLink}]]\n`;
+      const updatedWrapperBlock = 
+        wrapperBlockContent.slice(0, insertPos) + 
+        newEdgeGroup + 
+        wrapperBlockContent.slice(insertPos);
+      
+      // Replace wrapper block in section
+      const beforeWrapper = sectionLines.slice(0, wrapperStart).join("\n");
+      const afterWrapper = sectionLines.slice(wrapperEnd).join("\n");
+      const newSectionContent = beforeWrapper + "\n" + updatedWrapperBlock + "\n" + afterWrapper;
+      
+      // Replace section in full content
+      const beforeSection = lines.slice(0, section.startLine).join("\n");
+      const afterSection = lines.slice(section.endLine).join("\n");
+      const newContent = beforeSection + "\n" + newSectionContent + "\n" + afterSection;
+      console.log("[insertEdgeInSection] Setting new content with new edge group, length:", newContent.length);
+      editor.setValue(newContent);
+      console.log("[insertEdgeInSection] Content updated successfully");
+      return;
+    }
+  }
+
+  // Create new mapping block at end of section
+  console.log("[insertEdgeInSection] Creating new mapping block");
+  const existingMappings = new Map<string, string>();
+  const targetLinkBasename = targetLink.split("#")[0]?.split("|")[0]?.trim() || targetLink;
+  existingMappings.set(targetLinkBasename, edgeType);
+  console.log("[insertEdgeInSection] Target link basename:", targetLinkBasename);
+  
+  const newMappingBlock = buildMappingBlock(
+    [targetLinkBasename],
+    existingMappings,
+    {
+      wrapperCalloutType,
+      wrapperTitle,
+      wrapperFolded,
+      defaultEdgeType: settings.defaultEdgeType || "",
+      assignUnmapped: "none",
+    }
+  );
+  console.log("[insertEdgeInSection] New mapping block:", newMappingBlock ? "created" : "null");
+
+  if (!newMappingBlock) {
+    console.log("[insertEdgeInSection] Using fallback mapping block");
+    // Fallback
+    const foldMarker = wrapperFolded ? "-" : "+";
+    const mappingBlock = `\n\n> [!${wrapperCalloutType}]${foldMarker} ${wrapperTitle}\n>> [!edge] ${edgeType}\n>> [[${targetLink}]]\n`;
+    const newSectionContent = section.content.trimEnd() + mappingBlock;
+    
+    const beforeSection = lines.slice(0, section.startLine).join("\n");
+    const afterSection = lines.slice(section.endLine).join("\n");
+    const newContent = beforeSection + "\n" + newSectionContent + "\n" + afterSection;
+    console.log("[insertEdgeInSection] Setting fallback content, length:", newContent.length);
+    editor.setValue(newContent);
+    console.log("[insertEdgeInSection] Fallback content updated");
+    return;
+  }
+
+  const newSectionContent = insertMappingBlock(section.content, newMappingBlock);
+  console.log("[insertEdgeInSection] New section content length:", newSectionContent.length);
+
+  // Replace section in content
+  const beforeSection = lines.slice(0, section.startLine).join("\n");
+  const afterSection = lines.slice(section.endLine).join("\n");
+  const newContent = beforeSection + "\n" + newSectionContent + "\n" + afterSection;
+  console.log("[insertEdgeInSection] Final content length:", newContent.length);
+  editor.setValue(newContent);
+  console.log("[insertEdgeInSection] Content updated successfully");
+}
+
+/**
+ * Promote candidate edge to explicit edge.
+ */
+export async function promoteCandidate(
+  app: App,
+  editor: Editor,
+  file: TFile,
+  todo: CandidateCleanupTodo,
+  settings: any
+): Promise<void> {
+  const content = editor.getValue();
+
+  // Find candidates zone
+  const candidatesZone = await detectZone(app, file, "candidates");
+  if (!candidatesZone.exists) {
+    throw new Error("Candidates zone not found");
+  }
+
+  // Find candidate edge in zone
+  const candidateEdge = todo.candidateEdge;
+  const edgeType = candidateEdge.rawEdgeType;
+  const targetLink = candidateEdge.to.heading
+    ? `[[${candidateEdge.to.file}#${candidateEdge.to.heading}]]`
+    : `[[${candidateEdge.to.file}]]`;
+
+  // Determine source section (from evidence or current context)
+  const sourceSectionHeading = candidateEdge.evidence.sectionHeading;
+  const sourceSection = await findSection(app, file, sourceSectionHeading);
+
+  if (!sourceSection) {
+    throw new Error(`Source section not found: ${sourceSectionHeading}`);
+  }
+
+  // Insert edge in source section
+  await insertEdgeInSection(app, editor, file, sourceSection, edgeType, targetLink, settings);
+
+  // Remove candidate edge if keepOriginal is false
+  if (!settings.fixActions?.promoteCandidate?.keepOriginal) {
+    const lines = content.split(/\r?\n/);
+    const candidateLineStart = candidateEdge.evidence.lineRange?.start || candidatesZone.startLine;
+    const candidateLineEnd = candidateEdge.evidence.lineRange?.end || candidatesZone.endLine;
+
+    // Remove candidate edge lines
+    lines.splice(candidateLineStart, candidateLineEnd - candidateLineStart + 1);
+    editor.setValue(lines.join("\n"));
+  }
+}
+
+/**
+ * Filter suggested edge types by direction and note types.
+ * 
+ * @param suggestedTypes - Edge types from chain_roles
+ * @param edgeVocabulary - Edge vocabulary to check inverses
+ * @param sourceType - Source note type
+ * @param targetType - Target note type
+ * @param graphSchema - Graph schema for type compatibility
+ * @param direction - "forward" for insert_edge_forward, "backward" for insert_edge_inverse
+ */
+async function filterSuggestedEdgeTypes(
+  suggestedTypes: string[],
+  edgeVocabulary: EdgeVocabulary,
+  sourceType: string | null,
+  targetType: string | null,
+  graphSchema: any,
+  direction: "forward" | "backward" = "forward"
+): Promise<string[]> {
+  // Step 1: Filter by direction
+  // For forward: keep only types that are NOT inverses of other suggested types
+  // For backward: keep only types that ARE inverses of other suggested types, or have no inverse defined
+  const filteredByDirection: string[] = [];
+  
+  if (direction === "forward") {
+    // Forward: Keep types that are forward-direction (not inverses)
+    // Strategy: If a type has an inverse that's also in suggestedTypes, prefer the one that's NOT the inverse
+    const suggestedSet = new Set(suggestedTypes);
+    const processedPairs = new Set<string>();
+    
+    for (const type of suggestedTypes) {
+      const entry = edgeVocabulary.byCanonical.get(type);
+      if (entry?.inverse && suggestedSet.has(entry.inverse)) {
+        // Both type and its inverse are in the list - we have a pair
+        // For forward, prefer the type that is NOT the inverse of the other
+        // Create a canonical pair key (sorted)
+        const pairKey = [type, entry.inverse].sort().join("|");
+        if (!processedPairs.has(pairKey)) {
+          processedPairs.add(pairKey);
+          // For forward direction, keep the type that appears first in the list
+          // (assuming chain_roles lists forward types first)
+          const typeIndex = suggestedTypes.indexOf(type);
+          const inverseIndex = suggestedTypes.indexOf(entry.inverse);
+          if (typeIndex < inverseIndex) {
+            // Type appears first, keep it for forward
+            filteredByDirection.push(type);
+          } else {
+            // Inverse appears first, keep the inverse for forward (it's actually the forward type)
+            filteredByDirection.push(entry.inverse);
+          }
+        }
+      } else if (!entry?.inverse) {
+        // No inverse defined, keep it (bidirectional or forward-only)
+        filteredByDirection.push(type);
+      } else if (entry.inverse && !suggestedSet.has(entry.inverse)) {
+        // Has inverse but inverse is not in suggested list - this is likely forward
+        filteredByDirection.push(type);
+      }
+    }
+  } else {
+    // Backward: Keep types that are backward-direction (inverses)
+    const suggestedSet = new Set(suggestedTypes);
+    const processedPairs = new Set<string>();
+    
+    for (const type of suggestedTypes) {
+      const entry = edgeVocabulary.byCanonical.get(type);
+      if (entry?.inverse && suggestedSet.has(entry.inverse)) {
+        // Both type and its inverse are in the list
+        const pairKey = [type, entry.inverse].sort().join("|");
+        if (!processedPairs.has(pairKey)) {
+          processedPairs.add(pairKey);
+          // For backward direction, keep the type that appears second (the inverse)
+          const typeIndex = suggestedTypes.indexOf(type);
+          const inverseIndex = suggestedTypes.indexOf(entry.inverse);
+          if (typeIndex > inverseIndex) {
+            // Type appears second, keep it for backward
+            filteredByDirection.push(type);
+          } else {
+            // Inverse appears second, keep the inverse for backward
+            filteredByDirection.push(entry.inverse);
+          }
+        }
+      } else if (entry?.inverse && !suggestedSet.has(entry.inverse)) {
+        // Has inverse but inverse is not in suggested list - this might be backward
+        // Check if this type is the inverse of another suggested type
+        let isInverseOfSuggested = false;
+        for (const otherType of suggestedTypes) {
+          const otherEntry = edgeVocabulary.byCanonical.get(otherType);
+          if (otherEntry?.inverse === type) {
+            isInverseOfSuggested = true;
+            break;
+          }
+        }
+        if (isInverseOfSuggested) {
+          filteredByDirection.push(type);
+        }
+      } else if (!entry?.inverse) {
+        // No inverse defined, might be bidirectional - include it
+        filteredByDirection.push(type);
+      }
+    }
+  }
+  
+  // Step 2: Filter by note type compatibility using graph schema
+  if (graphSchema && sourceType && targetType) {
+    const { computeEdgeSuggestions } = await import("../mapping/schemaHelper");
+    const schemaSuggestions = computeEdgeSuggestions(
+      edgeVocabulary,
+      sourceType,
+      targetType,
+      graphSchema
+    );
+    
+    // Keep only suggested types that are either:
+    // - In typical (recommended for this source->target)
+    // - Not prohibited
+    // - Or if no schema suggestions, keep all
+    const finalFiltered: string[] = [];
+    for (const type of filteredByDirection) {
+      const isTypical = schemaSuggestions.typical.includes(type);
+      const isProhibited = schemaSuggestions.prohibited.includes(type);
+      
+      if (schemaSuggestions.typical.length > 0) {
+        // Schema has recommendations: prefer typical, avoid prohibited
+        if (isTypical || (!isProhibited && filteredByDirection.length <= 3)) {
+          // Keep if typical, or if not prohibited and we don't have many options
+          finalFiltered.push(type);
+        }
+      } else {
+        // No schema recommendations: keep all (unless prohibited)
+        if (!isProhibited) {
+          finalFiltered.push(type);
+        }
+      }
+    }
+    
+    // If we filtered everything out, fall back to direction-filtered list
+    return finalFiltered.length > 0 ? finalFiltered : filteredByDirection;
+  }
+  
+  // No schema filtering, return direction-filtered
+  return filteredByDirection.length > 0 ? filteredByDirection : suggestedTypes;
+}
+
+/**
+ * Choose edge type from suggestions.
+ */
+async function chooseEdgeType(
+  app: App,
+  edgeVocabulary: EdgeVocabulary,
+  suggestedTypes: string[],
+  sourceType: string | null = null,
+  targetType: string | null = null,
+  graphSchema: any = null,
+  direction: "forward" | "backward" = "forward"
+): Promise<string | null> {
+  console.log("[chooseEdgeType] Starting, suggestedTypes:", suggestedTypes);
+  console.log("[chooseEdgeType] sourceType:", sourceType, "targetType:", targetType, "direction:", direction);
+  console.log("[chooseEdgeType] edgeVocabulary entries:", edgeVocabulary.byCanonical.size);
+  
+  // Filter suggested types by direction and note types
+  const filteredSuggestedTypes = await filterSuggestedEdgeTypes(
+    suggestedTypes,
+    edgeVocabulary,
+    sourceType,
+    targetType,
+    graphSchema,
+    direction
+  );
+  console.log("[chooseEdgeType] Filtered suggested types:", filteredSuggestedTypes);
+  
+  // Show edge type chooser with filtered suggested types
+  const modal = new EdgeTypeChooserModal(
+    app,
+    edgeVocabulary,
+    sourceType,
+    targetType,
+    graphSchema,
+    filteredSuggestedTypes // Pass filtered suggested types to modal
+  );
+  
+  console.log("[chooseEdgeType] Modal created, calling show()...");
+  const result = await modal.show();
+  console.log("[chooseEdgeType] Modal result:", result);
+  
+  // Return alias if selected, otherwise canonical
+  if (!result) {
+    console.log("[chooseEdgeType] No result, returning null");
+    return null;
+  }
+  
+  const selectedType = result.alias || result.edgeType;
+  console.log("[chooseEdgeType] Returning selected type:", selectedType);
+  return selectedType;
+}

src/workbench/zoneDetector.ts

@@ -0,0 +1,160 @@
+/**
+ * Zone detection for writer operations.
+ */
+
+import type { App, TFile } from "obsidian";
+
+export interface ZoneInfo {
+  exists: boolean;
+  heading: string;
+  startLine: number;
+  endLine: number;
+  content: string;
+}
+
+/**
+ * Detect if a zone exists in a file.
+ */
+export async function detectZone(
+  app: App,
+  file: TFile,
+  zoneType: "candidates" | "note_links"
+): Promise<ZoneInfo> {
+  const content = await app.vault.read(file);
+  const lines = content.split(/\r?\n/);
+
+  const heading = zoneType === "candidates" ? "## Kandidaten" : "## Note-Verbindungen";
+
+  let startLine = -1;
+  let endLine = -1;
+
+  for (let i = 0; i < lines.length; i++) {
+    const line = lines[i];
+    if (!line) continue;
+
+    // Check for exact heading match
+    if (line.trim() === heading) {
+      startLine = i;
+      // Find end of section (next H2 or end of file)
+      for (let j = i + 1; j < lines.length; j++) {
+        const nextLine = lines[j];
+        if (!nextLine) continue;
+        if (nextLine.match(/^##\s+/)) {
+          endLine = j;
+          break;
+        }
+      }
+      if (endLine === -1) {
+        endLine = lines.length;
+      }
+      break;
+    }
+  }
+
+  if (startLine === -1) {
+    return {
+      exists: false,
+      heading,
+      startLine: -1,
+      endLine: -1,
+      content: "",
+    };
+  }
+
+  const zoneContent = lines.slice(startLine, endLine).join("\n");
+
+  return {
+    exists: true,
+    heading,
+    startLine,
+    endLine,
+    content: zoneContent,
+  };
+}
+
+/**
+ * Find section by heading in file.
+ */
+export async function findSection(
+  app: App,
+  file: TFile,
+  heading: string | null
+): Promise<ZoneInfo | null> {
+  if (heading === null) {
+    // Root section (before first heading)
+    const content = await app.vault.read(file);
+    const lines = content.split(/\r?\n/);
+
+    // Find first heading
+    let firstHeadingLine = -1;
+    for (let i = 0; i < lines.length; i++) {
+      const line = lines[i];
+      if (!line) continue;
+      if (line.match(/^##\s+/)) {
+        firstHeadingLine = i;
+        break;
+      }
+    }
+
+    if (firstHeadingLine === -1) {
+      firstHeadingLine = lines.length;
+    }
+
+    return {
+      exists: true,
+      heading: "",
+      startLine: 0,
+      endLine: firstHeadingLine,
+      content: lines.slice(0, firstHeadingLine).join("\n"),
+    };
+  }
+
+  const content = await app.vault.read(file);
+  const lines = content.split(/\r?\n/);
+
+  let startLine = -1;
+  let endLine = -1;
+
+  for (let i = 0; i < lines.length; i++) {
+    const line = lines[i];
+    if (!line) continue;
+
+    // Check for heading match (exact or with different levels)
+    const headingMatch = line.match(/^(#{1,6})\s+(.+)$/);
+    if (headingMatch && headingMatch[2]?.trim() === heading) {
+      startLine = i;
+      // Find end of section (next heading of same or higher level)
+      const headingLevel = headingMatch[1]?.length || 0;
+      for (let j = i + 1; j < lines.length; j++) {
+        const nextLine = lines[j];
+        if (!nextLine) continue;
+        const nextHeadingMatch = nextLine.match(/^(#{1,6})\s+(.+)$/);
+        if (nextHeadingMatch) {
+          const nextLevel = nextHeadingMatch[1]?.length || 0;
+          if (nextLevel > 0 && nextLevel <= headingLevel) {
+            endLine = j;
+            break;
+          }
+        }
+      }
+      if (endLine === -1) {
+        endLine = lines.length;
+      }
+      break;
+    }
+  }
+
+  if (startLine === -1) {
+    return null;
+  }
+
+  const sectionContent = lines.slice(startLine, endLine).join("\n");
+
+  return {
+    exists: true,
+    heading,
+    startLine,
+    endLine,
+    content: sectionContent,
+  };
+}