Protokoll #30737

ID30737
Zeitstempel2025-12-30 23:28:51.771284
Clientroot
IP145.224.72.245
Modellclaude-sonnet-4-20250514
Statuscompleted
Tokens9,254 (Input: 2,571, Output: 6,683)
Dauer88 ms
Request-Zeit2025-12-30 23:28:51.771284
Response-Zeit2025-12-30 23:28:51.859334

Request

{
    "event": "PreToolUse",
    "tool_name": "Edit",
    "tool_input": {
        "file_path": "\/var\/www\/scripts\/pipeline\/generators\/config_loader.py",
        "old_string": "def parse_structure(config: dict) -> tuple[str, str, list[str]]:\n    \"\"\"Parse new-style structure profile into prompt text and format info.\"\"\"\n    sections = []\n    output_format = None\n    erlaubte_tags = []\n\n    # Ausgabe-Format\n    ausgabe = config.get(\"ausgabe\", {})\n    if ausgabe:\n        output_format = ausgabe.get(\"format\", \"markdown\")\n        erlaubte_tags = ausgabe.get(\"erlaubte_tags\", [])\n        verbotene_tags = ausgabe.get(\"verbotene_tags\", [])\n\n        if output_format == \"body-html\":\n            sections.append(f\"\"\"### Ausgabe-Format: HTML\n- **Nur diese Tags verwenden:** {\", \".join(erlaubte_tags)}\n- **Verboten:** {\", \".join(verbotene_tags)}\n- {ausgabe.get(\"hinweis\", \"Sauberes semantisches HTML\")}\"\"\")\n\n    # Gesamtaufbau\n    aufbau = config.get(\"gesamtaufbau\", {})\n    if aufbau:\n        sections.append(f\"\"\"### Gesamtaufbau:\n- Form: {aufbau.get(\"form\", \"\")}\n- Dramaturgie: {aufbau.get(\"dramaturgie\", \"\")}\n- Linearität: {aufbau.get(\"linearitaet\", \"\")}\n- Themensprünge: {aufbau.get(\"themenspruenge\", \"\")}\"\"\")\n\n    # Einstieg\n    einstieg = config.get(\"einstieg\", {})\n    if einstieg:\n        sections.append(f\"\"\"### Einstieg:\n- Funktion: {einstieg.get(\"funktion\", \"\")}\n- Inhaltstyp: {einstieg.get(\"inhaltstyp\", \"\")}\n- Ausschluss: {einstieg.get(\"ausschluss\", \"\")}\"\"\")\n\n    # Hauptteil-Blöcke\n    hauptteil = config.get(\"hauptteil\", {})\n    bloecke = hauptteil.get(\"bloecke\", [])\n    if bloecke:\n        bloecke_text = \"\\n\".join(\n            [f\"  {i + 1}. {b.get('fokus', '')} → {b.get('ziel', '')}\" for i, b in enumerate(bloecke)]\n        )\n        sections.append(f\"\"\"### Hauptteil-Struktur:\n{bloecke_text}\"\"\")\n\n    # Schluss\n    schluss = config.get(\"schluss\", {})\n    if schluss:\n        sections.append(f\"\"\"### Schluss:\n- Typ: {schluss.get(\"typ\", \"\")}\n- Funktion: {schluss.get(\"funktion\", \"\")}\n- Abgrenzung: {schluss.get(\"abgrenzung\", \"\")}\"\"\")\n\n    # Formatierung\n    formatierung = config.get(\"formatierung\", {})\n    if formatierung:\n        ausschluss = formatierung.get(\"ausschluss\", [])\n        if ausschluss:\n            sections.append(f\"\"\"### Formatierung verboten:\n{\", \".join(ausschluss)}\"\"\")\n\n    return \"\\n\\n\".join(sections), output_format, erlaubte_tags",
        "new_string": "def parse_structure(config: dict) -> tuple[str, str, list[str]]:\n    \"\"\"Parse structure profile into prompt text and format info.\n\n    Supports both formats:\n    - Blog\/HTML format: gesamtaufbau, einstieg, hauptteil.bloecke, schluss, formatierung.ausschluss\n    - LinkedIn format: aufbau.hook, aufbau.hauptteil, aufbau.schluss, formatierung.*, verboten[]\n    \"\"\"\n    sections = []\n    output_format = None\n    erlaubte_tags = []\n\n    # WICHTIG field (LinkedIn format)\n    wichtig = config.get(\"WICHTIG\")\n    if wichtig:\n        sections.append(f\"### WICHTIG:\\n{wichtig}\")\n\n    # Ausgabe-Format\n    ausgabe = config.get(\"ausgabe\", {})\n    if ausgabe:\n        output_format = ausgabe.get(\"format\", \"markdown\")\n        erlaubte_tags = ausgabe.get(\"erlaubte_tags\", [])\n        verbotene_tags = ausgabe.get(\"verbotene_tags\", [])\n\n        if output_format == \"body-html\":\n            sections.append(f\"\"\"### Ausgabe-Format: HTML\n- **Nur diese Tags verwenden:** {\", \".join(erlaubte_tags)}\n- **Verboten:** {\", \".join(verbotene_tags)}\n- {ausgabe.get(\"hinweis\", \"Sauberes semantisches HTML\")}\"\"\")\n        elif output_format == \"reiner Text\":\n            # LinkedIn plain text format\n            zeichen_info = \"\"\n            if ausgabe.get(\"zeichen_min\") and ausgabe.get(\"zeichen_max\"):\n                zeichen_info = f\"\\n- Länge: {ausgabe.get('zeichen_min')}-{ausgabe.get('zeichen_max')} Zeichen\"\n            if ausgabe.get(\"woerter\"):\n                zeichen_info += f\" ({ausgabe.get('woerter')} Wörter)\"\n            sections.append(f\"\"\"### Ausgabe-Format: Reiner Text\n- KEIN Markdown, KEINE Formatierung\n- Keine **Fettschrift**, keine *Kursivschrift*\n- Keine Überschriften mit # oder ##\n- Nur Fließtext und einfache Zeilenumbrüche{zeichen_info}\"\"\")\n\n    # Try Blog format first: gesamtaufbau\n    aufbau = config.get(\"gesamtaufbau\", {})\n    if aufbau:\n        sections.append(f\"\"\"### Gesamtaufbau:\n- Form: {aufbau.get(\"form\", \"\")}\n- Dramaturgie: {aufbau.get(\"dramaturgie\", \"\")}\n- Linearität: {aufbau.get(\"linearitaet\", \"\")}\n- Themensprünge: {aufbau.get(\"themenspruenge\", \"\")}\"\"\")\n\n    # Try LinkedIn format: aufbau (with nested hook, hauptteil, etc.)\n    linkedin_aufbau = config.get(\"aufbau\", {})\n    if linkedin_aufbau and not aufbau:  # Only if gesamtaufbau not present\n        aufbau_sections = []\n\n        # Hook\n        hook = linkedin_aufbau.get(\"hook\", {})\n        if hook:\n            hook_text = f\"### Hook ({hook.get('position', 'Anfang')}):\\n\"\n            hook_text += f\"- Stil: {hook.get('stil', '')}\\n\"\n            if hook.get(\"beispiele\"):\n                hook_text += f\"- Beispiele: {'; '.join(hook['beispiele'][:2])}\\n\"\n            if hook.get(\"verboten\"):\n                hook_text += f\"- Verboten: {', '.join(hook['verboten'])}\"\n            aufbau_sections.append(hook_text)\n\n        # Praxisbezug\n        praxis = linkedin_aufbau.get(\"praxisbezug\", {})\n        if praxis:\n            praxis_text = f\"### Praxisbezug ({praxis.get('position', '')}):\\n\"\n            praxis_text += f\"- Stil: {praxis.get('stil', '')}\\n\"\n            if praxis.get(\"muster\"):\n                praxis_text += f\"- Muster: {'; '.join(praxis['muster'][:2])}\"\n            aufbau_sections.append(praxis_text)\n\n        # Hauptteil\n        hauptteil = linkedin_aufbau.get(\"hauptteil\", {})\n        if hauptteil:\n            hauptteil_text = \"### Hauptteil:\\n\"\n            if hauptteil.get(\"struktur\"):\n                hauptteil_text += f\"- Struktur: {hauptteil.get('struktur')}\\n\"\n            if hauptteil.get(\"theoretische_einordnung\"):\n                hauptteil_text += f\"- Theorie: {hauptteil.get('theoretische_einordnung')}\\n\"\n            if hauptteil.get(\"differenzierung\"):\n                hauptteil_text += f\"- Differenzierung: {hauptteil.get('differenzierung')}\\n\"\n            if hauptteil.get(\"dreier_struktur\"):\n                hauptteil_text += f\"- Dreier-Struktur: {hauptteil.get('dreier_struktur')}\"\n            aufbau_sections.append(hauptteil_text)\n\n        # Handlungsempfehlung\n        handlung = linkedin_aufbau.get(\"handlungsempfehlung\", {})\n        if handlung:\n            handlung_text = \"### Handlungsempfehlung:\\n\"\n            handlung_text += f\"- Stil: {handlung.get('stil', '')}\\n\"\n            if handlung.get(\"muster\"):\n                handlung_text += f\"- Muster: {'; '.join(handlung['muster'][:2])}\"\n            aufbau_sections.append(handlung_text)\n\n        # Schluss (LinkedIn style)\n        schluss = linkedin_aufbau.get(\"schluss\", {})\n        if schluss:\n            schluss_text = \"### Schluss:\\n\"\n            if schluss.get(\"soft_cta\"):\n                schluss_text += f\"- Stil: {schluss.get('soft_cta')}\\n\"\n            if schluss.get(\"muster\"):\n                schluss_text += f\"- Muster: {'; '.join(schluss['muster'][:2])}\\n\"\n            if schluss.get(\"verboten\"):\n                schluss_text += f\"- Verboten: {', '.join(schluss['verboten'])}\"\n            aufbau_sections.append(schluss_text)\n\n        sections.extend(aufbau_sections)\n\n    # Blog format: Einstieg\n    einstieg = config.get(\"einstieg\", {})\n    if einstieg:\n        sections.append(f\"\"\"### Einstieg:\n- Funktion: {einstieg.get(\"funktion\", \"\")}\n- Inhaltstyp: {einstieg.get(\"inhaltstyp\", \"\")}\n- Ausschluss: {einstieg.get(\"ausschluss\", \"\")}\"\"\")\n\n    # Blog format: Hauptteil-Blöcke\n    hauptteil = config.get(\"hauptteil\", {})\n    bloecke = hauptteil.get(\"bloecke\", [])\n    if bloecke:\n        bloecke_text = \"\\n\".join(\n            [f\"  {i + 1}. {b.get('fokus', '')} → {b.get('ziel', '')}\" for i, b in enumerate(bloecke)]\n        )\n        sections.append(f\"\"\"### Hauptteil-Struktur:\n{bloecke_text}\"\"\")\n\n    # Blog format: Schluss\n    schluss = config.get(\"schluss\", {})\n    if schluss:\n        sections.append(f\"\"\"### Schluss:\n- Typ: {schluss.get(\"typ\", \"\")}\n- Funktion: {schluss.get(\"funktion\", \"\")}\n- Abgrenzung: {schluss.get(\"abgrenzung\", \"\")}\"\"\")\n\n    # Formatierung - handle both styles\n    formatierung = config.get(\"formatierung\", {})\n    if formatierung:\n        # Blog format: ausschluss array\n        ausschluss = formatierung.get(\"ausschluss\", [])\n        if ausschluss:\n            sections.append(f\"\"\"### Formatierung verboten:\n{\", \".join(ausschluss)}\"\"\")\n\n        # LinkedIn format: individual fields\n        verbote = []\n        if formatierung.get(\"emojis\") == \"verboten\" or \"verboten\" in str(formatierung.get(\"emojis\", \"\")):\n            verbote.append(\"Emojis\")\n        if formatierung.get(\"fettschrift\") == \"verboten\" or \"verboten\" in str(formatierung.get(\"fettschrift\", \"\")):\n            verbote.append(\"Fettschrift (**text**)\")\n        if formatierung.get(\"markdown\") == \"verboten\" or \"verboten\" in str(formatierung.get(\"markdown\", \"\")):\n            verbote.append(\"Markdown-Formatierung\")\n        if formatierung.get(\"hashtags\") == \"keine\":\n            verbote.append(\"Hashtags\")\n\n        if verbote and not ausschluss:  # Only add if not already handled by ausschluss\n            sections.append(f\"\"\"### Formatierung STRIKT verboten:\n{\", \".join(verbote)}\"\"\")\n\n    # Top-level verboten array (LinkedIn format)\n    verboten = config.get(\"verboten\", [])\n    if verboten:\n        sections.append(f\"\"\"### VERBOTEN (strikt einhalten!):\n- {chr(10).join(['- ' + v if not v.startswith('-') else v for v in verboten])}\"\"\")\n\n    return \"\\n\\n\".join(sections), output_format, erlaubte_tags"
    }
}

Response

{
    "tool_response": {
        "filePath": "\/var\/www\/scripts\/pipeline\/generators\/config_loader.py",
        "oldString": "def parse_structure(config: dict) -> tuple[str, str, list[str]]:\n    \"\"\"Parse new-style structure profile into prompt text and format info.\"\"\"\n    sections = []\n    output_format = None\n    erlaubte_tags = []\n\n    # Ausgabe-Format\n    ausgabe = config.get(\"ausgabe\", {})\n    if ausgabe:\n        output_format = ausgabe.get(\"format\", \"markdown\")\n        erlaubte_tags = ausgabe.get(\"erlaubte_tags\", [])\n        verbotene_tags = ausgabe.get(\"verbotene_tags\", [])\n\n        if output_format == \"body-html\":\n            sections.append(f\"\"\"### Ausgabe-Format: HTML\n- **Nur diese Tags verwenden:** {\", \".join(erlaubte_tags)}\n- **Verboten:** {\", \".join(verbotene_tags)}\n- {ausgabe.get(\"hinweis\", \"Sauberes semantisches HTML\")}\"\"\")\n\n    # Gesamtaufbau\n    aufbau = config.get(\"gesamtaufbau\", {})\n    if aufbau:\n        sections.append(f\"\"\"### Gesamtaufbau:\n- Form: {aufbau.get(\"form\", \"\")}\n- Dramaturgie: {aufbau.get(\"dramaturgie\", \"\")}\n- Linearität: {aufbau.get(\"linearitaet\", \"\")}\n- Themensprünge: {aufbau.get(\"themenspruenge\", \"\")}\"\"\")\n\n    # Einstieg\n    einstieg = config.get(\"einstieg\", {})\n    if einstieg:\n        sections.append(f\"\"\"### Einstieg:\n- Funktion: {einstieg.get(\"funktion\", \"\")}\n- Inhaltstyp: {einstieg.get(\"inhaltstyp\", \"\")}\n- Ausschluss: {einstieg.get(\"ausschluss\", \"\")}\"\"\")\n\n    # Hauptteil-Blöcke\n    hauptteil = config.get(\"hauptteil\", {})\n    bloecke = hauptteil.get(\"bloecke\", [])\n    if bloecke:\n        bloecke_text = \"\\n\".join(\n            [f\"  {i + 1}. {b.get('fokus', '')} → {b.get('ziel', '')}\" for i, b in enumerate(bloecke)]\n        )\n        sections.append(f\"\"\"### Hauptteil-Struktur:\n{bloecke_text}\"\"\")\n\n    # Schluss\n    schluss = config.get(\"schluss\", {})\n    if schluss:\n        sections.append(f\"\"\"### Schluss:\n- Typ: {schluss.get(\"typ\", \"\")}\n- Funktion: {schluss.get(\"funktion\", \"\")}\n- Abgrenzung: {schluss.get(\"abgrenzung\", \"\")}\"\"\")\n\n    # Formatierung\n    formatierung = config.get(\"formatierung\", {})\n    if formatierung:\n        ausschluss = formatierung.get(\"ausschluss\", [])\n        if ausschluss:\n            sections.append(f\"\"\"### Formatierung verboten:\n{\", \".join(ausschluss)}\"\"\")\n\n    return \"\\n\\n\".join(sections), output_format, erlaubte_tags",
        "newString": "def parse_structure(config: dict) -> tuple[str, str, list[str]]:\n    \"\"\"Parse structure profile into prompt text and format info.\n\n    Supports both formats:\n    - Blog\/HTML format: gesamtaufbau, einstieg, hauptteil.bloecke, schluss, formatierung.ausschluss\n    - LinkedIn format: aufbau.hook, aufbau.hauptteil, aufbau.schluss, formatierung.*, verboten[]\n    \"\"\"\n    sections = []\n    output_format = None\n    erlaubte_tags = []\n\n    # WICHTIG field (LinkedIn format)\n    wichtig = config.get(\"WICHTIG\")\n    if wichtig:\n        sections.append(f\"### WICHTIG:\\n{wichtig}\")\n\n    # Ausgabe-Format\n    ausgabe = config.get(\"ausgabe\", {})\n    if ausgabe:\n        output_format = ausgabe.get(\"format\", \"markdown\")\n        erlaubte_tags = ausgabe.get(\"erlaubte_tags\", [])\n        verbotene_tags = ausgabe.get(\"verbotene_tags\", [])\n\n        if output_format == \"body-html\":\n            sections.append(f\"\"\"### Ausgabe-Format: HTML\n- **Nur diese Tags verwenden:** {\", \".join(erlaubte_tags)}\n- **Verboten:** {\", \".join(verbotene_tags)}\n- {ausgabe.get(\"hinweis\", \"Sauberes semantisches HTML\")}\"\"\")\n        elif output_format == \"reiner Text\":\n            # LinkedIn plain text format\n            zeichen_info = \"\"\n            if ausgabe.get(\"zeichen_min\") and ausgabe.get(\"zeichen_max\"):\n                zeichen_info = f\"\\n- Länge: {ausgabe.get('zeichen_min')}-{ausgabe.get('zeichen_max')} Zeichen\"\n            if ausgabe.get(\"woerter\"):\n                zeichen_info += f\" ({ausgabe.get('woerter')} Wörter)\"\n            sections.append(f\"\"\"### Ausgabe-Format: Reiner Text\n- KEIN Markdown, KEINE Formatierung\n- Keine **Fettschrift**, keine *Kursivschrift*\n- Keine Überschriften mit # oder ##\n- Nur Fließtext und einfache Zeilenumbrüche{zeichen_info}\"\"\")\n\n    # Try Blog format first: gesamtaufbau\n    aufbau = config.get(\"gesamtaufbau\", {})\n    if aufbau:\n        sections.append(f\"\"\"### Gesamtaufbau:\n- Form: {aufbau.get(\"form\", \"\")}\n- Dramaturgie: {aufbau.get(\"dramaturgie\", \"\")}\n- Linearität: {aufbau.get(\"linearitaet\", \"\")}\n- Themensprünge: {aufbau.get(\"themenspruenge\", \"\")}\"\"\")\n\n    # Try LinkedIn format: aufbau (with nested hook, hauptteil, etc.)\n    linkedin_aufbau = config.get(\"aufbau\", {})\n    if linkedin_aufbau and not aufbau:  # Only if gesamtaufbau not present\n        aufbau_sections = []\n\n        # Hook\n        hook = linkedin_aufbau.get(\"hook\", {})\n        if hook:\n            hook_text = f\"### Hook ({hook.get('position', 'Anfang')}):\\n\"\n            hook_text += f\"- Stil: {hook.get('stil', '')}\\n\"\n            if hook.get(\"beispiele\"):\n                hook_text += f\"- Beispiele: {'; '.join(hook['beispiele'][:2])}\\n\"\n            if hook.get(\"verboten\"):\n                hook_text += f\"- Verboten: {', '.join(hook['verboten'])}\"\n            aufbau_sections.append(hook_text)\n\n        # Praxisbezug\n        praxis = linkedin_aufbau.get(\"praxisbezug\", {})\n        if praxis:\n            praxis_text = f\"### Praxisbezug ({praxis.get('position', '')}):\\n\"\n            praxis_text += f\"- Stil: {praxis.get('stil', '')}\\n\"\n            if praxis.get(\"muster\"):\n                praxis_text += f\"- Muster: {'; '.join(praxis['muster'][:2])}\"\n            aufbau_sections.append(praxis_text)\n\n        # Hauptteil\n        hauptteil = linkedin_aufbau.get(\"hauptteil\", {})\n        if hauptteil:\n            hauptteil_text = \"### Hauptteil:\\n\"\n            if hauptteil.get(\"struktur\"):\n                hauptteil_text += f\"- Struktur: {hauptteil.get('struktur')}\\n\"\n            if hauptteil.get(\"theoretische_einordnung\"):\n                hauptteil_text += f\"- Theorie: {hauptteil.get('theoretische_einordnung')}\\n\"\n            if hauptteil.get(\"differenzierung\"):\n                hauptteil_text += f\"- Differenzierung: {hauptteil.get('differenzierung')}\\n\"\n            if hauptteil.get(\"dreier_struktur\"):\n                hauptteil_text += f\"- Dreier-Struktur: {hauptteil.get('dreier_struktur')}\"\n            aufbau_sections.append(hauptteil_text)\n\n        # Handlungsempfehlung\n        handlung = linkedin_aufbau.get(\"handlungsempfehlung\", {})\n        if handlung:\n            handlung_text = \"### Handlungsempfehlung:\\n\"\n            handlung_text += f\"- Stil: {handlung.get('stil', '')}\\n\"\n            if handlung.get(\"muster\"):\n                handlung_text += f\"- Muster: {'; '.join(handlung['muster'][:2])}\"\n            aufbau_sections.append(handlung_text)\n\n        # Schluss (LinkedIn style)\n        schluss = linkedin_aufbau.get(\"schluss\", {})\n        if schluss:\n            schluss_text = \"### Schluss:\\n\"\n            if schluss.get(\"soft_cta\"):\n                schluss_text += f\"- Stil: {schluss.get('soft_cta')}\\n\"\n            if schluss.get(\"muster\"):\n                schluss_text += f\"- Muster: {'; '.join(schluss['muster'][:2])}\\n\"\n            if schluss.get(\"verboten\"):\n                schluss_text += f\"- Verboten: {', '.join(schluss['verboten'])}\"\n            aufbau_sections.append(schluss_text)\n\n        sections.extend(aufbau_sections)\n\n    # Blog format: Einstieg\n    einstieg = config.get(\"einstieg\", {})\n    if einstieg:\n        sections.append(f\"\"\"### Einstieg:\n- Funktion: {einstieg.get(\"funktion\", \"\")}\n- Inhaltstyp: {einstieg.get(\"inhaltstyp\", \"\")}\n- Ausschluss: {einstieg.get(\"ausschluss\", \"\")}\"\"\")\n\n    # Blog format: Hauptteil-Blöcke\n    hauptteil = config.get(\"hauptteil\", {})\n    bloecke = hauptteil.get(\"bloecke\", [])\n    if bloecke:\n        bloecke_text = \"\\n\".join(\n            [f\"  {i + 1}. {b.get('fokus', '')} → {b.get('ziel', '')}\" for i, b in enumerate(bloecke)]\n        )\n        sections.append(f\"\"\"### Hauptteil-Struktur:\n{bloecke_text}\"\"\")\n\n    # Blog format: Schluss\n    schluss = config.get(\"schluss\", {})\n    if schluss:\n        sections.append(f\"\"\"### Schluss:\n- Typ: {schluss.get(\"typ\", \"\")}\n- Funktion: {schluss.get(\"funktion\", \"\")}\n- Abgrenzung: {schluss.get(\"abgrenzung\", \"\")}\"\"\")\n\n    # Formatierung - handle both styles\n    formatierung = config.get(\"formatierung\", {})\n    if formatierung:\n        # Blog format: ausschluss array\n        ausschluss = formatierung.get(\"ausschluss\", [])\n        if ausschluss:\n            sections.append(f\"\"\"### Formatierung verboten:\n{\", \".join(ausschluss)}\"\"\")\n\n        # LinkedIn format: individual fields\n        verbote = []\n        if formatierung.get(\"emojis\") == \"verboten\" or \"verboten\" in str(formatierung.get(\"emojis\", \"\")):\n            verbote.append(\"Emojis\")\n        if formatierung.get(\"fettschrift\") == \"verboten\" or \"verboten\" in str(formatierung.get(\"fettschrift\", \"\")):\n            verbote.append(\"Fettschrift (**text**)\")\n        if formatierung.get(\"markdown\") == \"verboten\" or \"verboten\" in str(formatierung.get(\"markdown\", \"\")):\n            verbote.append(\"Markdown-Formatierung\")\n        if formatierung.get(\"hashtags\") == \"keine\":\n            verbote.append(\"Hashtags\")\n\n        if verbote and not ausschluss:  # Only add if not already handled by ausschluss\n            sections.append(f\"\"\"### Formatierung STRIKT verboten:\n{\", \".join(verbote)}\"\"\")\n\n    # Top-level verboten array (LinkedIn format)\n    verboten = config.get(\"verboten\", [])\n    if verboten:\n        sections.append(f\"\"\"### VERBOTEN (strikt einhalten!):\n- {chr(10).join(['- ' + v if not v.startswith('-') else v for v in verboten])}\"\"\")\n\n    return \"\\n\\n\".join(sections), output_format, erlaubte_tags",
        "originalFile": "\"\"\"\nConfiguration Loading Functions - Load prompts, profiles, contracts, structures.\n\"\"\"\n\nimport json\nimport sys\n\nsys.path.insert(0, \"\/var\/www\/scripts\/pipeline\")\n\nfrom db import db\n\n\ndef get_prompt(name: str) -> str | None:\n    \"\"\"Load prompt from database by name.\"\"\"\n    cursor = db.execute(\n        \"\"\"SELECT content FROM prompts WHERE name = %s AND is_active = 1 ORDER BY version DESC LIMIT 1\"\"\",\n        (name,),\n    )\n    result = cursor.fetchone()\n    cursor.close()\n    return result[\"content\"] if result else None\n\n\ndef get_config_item(item_id: int, item_type: str) -> dict | None:\n    \"\"\"Load configuration item from content_config table.\"\"\"\n    if not item_id:\n        return None\n\n    cursor = db.execute(\n        \"SELECT name, content FROM content_config WHERE id = %s AND type = %s AND status = 'active'\",\n        (item_id, item_type),\n    )\n    result = cursor.fetchone()\n    cursor.close()\n\n    if result:\n        config = json.loads(result[\"content\"]) if isinstance(result[\"content\"], str) else result[\"content\"]\n        return {\"name\": result[\"name\"], \"config\": config}\n    return None\n\n\ndef get_author_profile(profile_id: int) -> dict | None:\n    \"\"\"Load author profile from database.\"\"\"\n    return get_config_item(profile_id, \"author_profile\")\n\n\ndef get_contract(contract_id: int) -> dict | None:\n    \"\"\"Load content contract from database.\"\"\"\n    return get_config_item(contract_id, \"contract\")\n\n\ndef get_structure(structure_id: int) -> dict | None:\n    \"\"\"Load content structure from database.\"\"\"\n    result = get_config_item(structure_id, \"structure\")\n    if result:\n        # Structure has additional 'type' field in config\n        result[\"type\"] = result[\"config\"].get(\"type\", \"article\")\n    return result\n\n\ndef get_order(order_id: int) -> dict | None:\n    \"\"\"Load content order with all related data.\"\"\"\n    cursor = db.execute(\n        \"\"\"SELECT co.*,\n              ap.name as profile_name, ap.content as profile_config,\n              cc.name as contract_name, cc.content as contract_config,\n              cs.name as structure_name, cs.content as structure_config\n           FROM content_orders co\n           LEFT JOIN content_config ap ON co.author_profile_id = ap.id AND ap.type = 'author_profile'\n           LEFT JOIN content_config cc ON co.contract_id = cc.id AND cc.type = 'contract'\n           LEFT JOIN content_config cs ON co.structure_id = cs.id AND cs.type = 'structure'\n           WHERE co.id = %s\"\"\",\n        (order_id,),\n    )\n    result = cursor.fetchone()\n    cursor.close()\n    return result\n\n\ndef parse_author_profile(config: dict) -> str:\n    \"\"\"Parse new-style author profile (Cary format) into prompt text.\"\"\"\n    sections = []\n\n    # Haltung\n    haltung = config.get(\"haltung\", {})\n    if haltung:\n        sections.append(f\"\"\"### Haltung:\n- Grundhaltung: {haltung.get(\"grundhaltung\", \"\")}\n- Ausrichtung: {haltung.get(\"ausrichtung\", \"\")}\n- Spannungstoleranz: {haltung.get(\"spannungstoleranz\", \"\")}\n- Vereinfachung: {haltung.get(\"vereinfachung\", \"\")}\"\"\")\n\n    # Tonalität\n    tonalitaet = config.get(\"tonalitaet\", {})\n    if tonalitaet:\n        sections.append(f\"\"\"### Tonalität:\n- Charakter: {tonalitaet.get(\"charakter\", \"\")}\n- Stil: {tonalitaet.get(\"stil\", \"\")}\n- Wirkung: {tonalitaet.get(\"wirkung\", \"\")}\n- Abgrenzung: {tonalitaet.get(\"abgrenzung\", \"\")}\"\"\")\n\n    # Sprachmodus\n    sprachmodus = config.get(\"sprachmodus\", {})\n    if sprachmodus:\n        sections.append(f\"\"\"### Sprachmodus:\n- Denkstil: {sprachmodus.get(\"denkstil\", \"\")}\n- Aussagenform: {sprachmodus.get(\"aussagenform\", \"\")}\n- Fragenfunktion: {sprachmodus.get(\"fragenfunktion\", \"\")}\"\"\")\n\n    # Grammatik und Satzbau - WICHTIG für Verbote\n    grammatik = config.get(\"grammatik_und_satzbau\", {})\n    if grammatik:\n        verbote = []\n        if grammatik.get(\"stakkato\") == \"ausgeschlossen\":\n            verbote.append(\"Stakkato-Sätze\")\n        if grammatik.get(\"einschuebe\") == \"keine\":\n            verbote.append(\"Einschübe\")\n        if grammatik.get(\"gedankenstriche\") == \"verboten\":\n            verbote.append(\"Gedankenstriche (–)\")\n\n        sections.append(f\"\"\"### Grammatik und Satzbau:\n- Sätze: {grammatik.get(\"saetze\", \"\")}\n- Rhythmus: {grammatik.get(\"rhythmus\", \"\")}\n- **VERBOTEN:** {\", \".join(verbote) if verbote else \"keine\"}\"\"\")\n\n    # Wortwahl\n    wortwahl = config.get(\"wortwahl\", {})\n    if wortwahl:\n        verboten = []\n        if wortwahl.get(\"buzzwords\") == \"ausgeschlossen\":\n            verboten.append(\"Buzzwords\")\n        if wortwahl.get(\"methodennamen\") == \"ausgeschlossen\":\n            verboten.append(\"Methodennamen\")\n\n        sections.append(f\"\"\"### Wortwahl:\n- Niveau: {wortwahl.get(\"niveau\", \"\")}\n- Begriffe: {wortwahl.get(\"begriffe\", \"\")}\n- **VERBOTEN:** {\", \".join(verboten) if verboten else \"keine\"}\"\"\")\n\n    # Adressierung\n    adressierung = config.get(\"adressierung\", {})\n    if adressierung:\n        sections.append(f\"\"\"### Adressierung:\n- Form: {adressierung.get(\"form\", \"Sie\")}\n- Beziehung: {adressierung.get(\"beziehung\", \"\")}\n- Einladung: {adressierung.get(\"einladung\", \"\")}\"\"\")\n\n    # Metaphern\n    metaphern = config.get(\"metaphern\", {})\n    if metaphern:\n        sections.append(f\"\"\"### Metaphern:\n- Einsatz: {metaphern.get(\"einsatz\", \"\")}\n- Herkunft: {metaphern.get(\"herkunft\", \"\")}\n- Konsistenz: {metaphern.get(\"konsistenz\", \"\")}\"\"\")\n\n    return \"\\n\\n\".join(sections)\n\n\ndef parse_structure(config: dict) -> tuple[str, str, list[str]]:\n    \"\"\"Parse new-style structure profile into prompt text and format info.\"\"\"\n    sections = []\n    output_format = None\n    erlaubte_tags = []\n\n    # Ausgabe-Format\n    ausgabe = config.get(\"ausgabe\", {})\n    if ausgabe:\n        output_format = ausgabe.get(\"format\", \"markdown\")\n        erlaubte_tags = ausgabe.get(\"erlaubte_tags\", [])\n        verbotene_tags = ausgabe.get(\"verbotene_tags\", [])\n\n        if output_format == \"body-html\":\n            sections.append(f\"\"\"### Ausgabe-Format: HTML\n- **Nur diese Tags verwenden:** {\", \".join(erlaubte_tags)}\n- **Verboten:** {\", \".join(verbotene_tags)}\n- {ausgabe.get(\"hinweis\", \"Sauberes semantisches HTML\")}\"\"\")\n\n    # Gesamtaufbau\n    aufbau = config.get(\"gesamtaufbau\", {})\n    if aufbau:\n        sections.append(f\"\"\"### Gesamtaufbau:\n- Form: {aufbau.get(\"form\", \"\")}\n- Dramaturgie: {aufbau.get(\"dramaturgie\", \"\")}\n- Linearität: {aufbau.get(\"linearitaet\", \"\")}\n- Themensprünge: {aufbau.get(\"themenspruenge\", \"\")}\"\"\")\n\n    # Einstieg\n    einstieg = config.get(\"einstieg\", {})\n    if einstieg:\n        sections.append(f\"\"\"### Einstieg:\n- Funktion: {einstieg.get(\"funktion\", \"\")}\n- Inhaltstyp: {einstieg.get(\"inhaltstyp\", \"\")}\n- Ausschluss: {einstieg.get(\"ausschluss\", \"\")}\"\"\")\n\n    # Hauptteil-Blöcke\n    hauptteil = config.get(\"hauptteil\", {})\n    bloecke = hauptteil.get(\"bloecke\", [])\n    if bloecke:\n        bloecke_text = \"\\n\".join(\n            [f\"  {i + 1}. {b.get('fokus', '')} → {b.get('ziel', '')}\" for i, b in enumerate(bloecke)]\n        )\n        sections.append(f\"\"\"### Hauptteil-Struktur:\n{bloecke_text}\"\"\")\n\n    # Schluss\n    schluss = config.get(\"schluss\", {})\n    if schluss:\n        sections.append(f\"\"\"### Schluss:\n- Typ: {schluss.get(\"typ\", \"\")}\n- Funktion: {schluss.get(\"funktion\", \"\")}\n- Abgrenzung: {schluss.get(\"abgrenzung\", \"\")}\"\"\")\n\n    # Formatierung\n    formatierung = config.get(\"formatierung\", {})\n    if formatierung:\n        ausschluss = formatierung.get(\"ausschluss\", [])\n        if ausschluss:\n            sections.append(f\"\"\"### Formatierung verboten:\n{\", \".join(ausschluss)}\"\"\")\n\n    return \"\\n\\n\".join(sections), output_format, erlaubte_tags\n",
        "structuredPatch": [
            {
                "oldStart": 157,
                "oldLines": 11,
                "newStart": 157,
                "newLines": 21,
                "lines": [
                    " ",
                    " ",
                    " def parse_structure(config: dict) -> tuple[str, str, list[str]]:",
                    "-    \"\"\"Parse new-style structure profile into prompt text and format info.\"\"\"",
                    "+    \"\"\"Parse structure profile into prompt text and format info.",
                    "+",
                    "+    Supports both formats:",
                    "+    - Blog\/HTML format: gesamtaufbau, einstieg, hauptteil.bloecke, schluss, formatierung.ausschluss",
                    "+    - LinkedIn format: aufbau.hook, aufbau.hauptteil, aufbau.schluss, formatierung.*, verboten[]",
                    "+    \"\"\"",
                    "     sections = []",
                    "     output_format = None",
                    "     erlaubte_tags = []",
                    " ",
                    "+    # WICHTIG field (LinkedIn format)",
                    "+    wichtig = config.get(\"WICHTIG\")",
                    "+    if wichtig:",
                    "+        sections.append(f\"### WICHTIG:\\n{wichtig}\")",
                    "+",
                    "     # Ausgabe-Format",
                    "     ausgabe = config.get(\"ausgabe\", {})",
                    "     if ausgabe:"
                ]
            },
            {
                "oldStart": 174,
                "oldLines": 8,
                "newStart": 184,
                "newLines": 20,
                "lines": [
                    " - **Nur diese Tags verwenden:** {\", \".join(erlaubte_tags)}",
                    " - **Verboten:** {\", \".join(verbotene_tags)}",
                    " - {ausgabe.get(\"hinweis\", \"Sauberes semantisches HTML\")}\"\"\")",
                    "+        elif output_format == \"reiner Text\":",
                    "+            # LinkedIn plain text format",
                    "+            zeichen_info = \"\"",
                    "+            if ausgabe.get(\"zeichen_min\") and ausgabe.get(\"zeichen_max\"):",
                    "+                zeichen_info = f\"\\n- Länge: {ausgabe.get('zeichen_min')}-{ausgabe.get('zeichen_max')} Zeichen\"",
                    "+            if ausgabe.get(\"woerter\"):",
                    "+                zeichen_info += f\" ({ausgabe.get('woerter')} Wörter)\"",
                    "+            sections.append(f\"\"\"### Ausgabe-Format: Reiner Text",
                    "+- KEIN Markdown, KEINE Formatierung",
                    "+- Keine **Fettschrift**, keine *Kursivschrift*",
                    "+- Keine Überschriften mit # oder ##",
                    "+- Nur Fließtext und einfache Zeilenumbrüche{zeichen_info}\"\"\")",
                    " ",
                    "-    # Gesamtaufbau",
                    "+    # Try Blog format first: gesamtaufbau",
                    "     aufbau = config.get(\"gesamtaufbau\", {})",
                    "     if aufbau:",
                    "         sections.append(f\"\"\"### Gesamtaufbau:"
                ]
            },
            {
                "oldStart": 184,
                "oldLines": 7,
                "newStart": 206,
                "newLines": 69,
                "lines": [
                    " - Linearität: {aufbau.get(\"linearitaet\", \"\")}",
                    " - Themensprünge: {aufbau.get(\"themenspruenge\", \"\")}\"\"\")",
                    " ",
                    "-    # Einstieg",
                    "+    # Try LinkedIn format: aufbau (with nested hook, hauptteil, etc.)",
                    "+    linkedin_aufbau = config.get(\"aufbau\", {})",
                    "+    if linkedin_aufbau and not aufbau:  # Only if gesamtaufbau not present",
                    "+        aufbau_sections = []",
                    "+",
                    "+        # Hook",
                    "+        hook = linkedin_aufbau.get(\"hook\", {})",
                    "+        if hook:",
                    "+            hook_text = f\"### Hook ({hook.get('position', 'Anfang')}):\\n\"",
                    "+            hook_text += f\"- Stil: {hook.get('stil', '')}\\n\"",
                    "+            if hook.get(\"beispiele\"):",
                    "+                hook_text += f\"- Beispiele: {'; '.join(hook['beispiele'][:2])}\\n\"",
                    "+            if hook.get(\"verboten\"):",
                    "+                hook_text += f\"- Verboten: {', '.join(hook['verboten'])}\"",
                    "+            aufbau_sections.append(hook_text)",
                    "+",
                    "+        # Praxisbezug",
                    "+        praxis = linkedin_aufbau.get(\"praxisbezug\", {})",
                    "+        if praxis:",
                    "+            praxis_text = f\"### Praxisbezug ({praxis.get('position', '')}):\\n\"",
                    "+            praxis_text += f\"- Stil: {praxis.get('stil', '')}\\n\"",
                    "+            if praxis.get(\"muster\"):",
                    "+                praxis_text += f\"- Muster: {'; '.join(praxis['muster'][:2])}\"",
                    "+            aufbau_sections.append(praxis_text)",
                    "+",
                    "+        # Hauptteil",
                    "+        hauptteil = linkedin_aufbau.get(\"hauptteil\", {})",
                    "+        if hauptteil:",
                    "+            hauptteil_text = \"### Hauptteil:\\n\"",
                    "+            if hauptteil.get(\"struktur\"):",
                    "+                hauptteil_text += f\"- Struktur: {hauptteil.get('struktur')}\\n\"",
                    "+            if hauptteil.get(\"theoretische_einordnung\"):",
                    "+                hauptteil_text += f\"- Theorie: {hauptteil.get('theoretische_einordnung')}\\n\"",
                    "+            if hauptteil.get(\"differenzierung\"):",
                    "+                hauptteil_text += f\"- Differenzierung: {hauptteil.get('differenzierung')}\\n\"",
                    "+            if hauptteil.get(\"dreier_struktur\"):",
                    "+                hauptteil_text += f\"- Dreier-Struktur: {hauptteil.get('dreier_struktur')}\"",
                    "+            aufbau_sections.append(hauptteil_text)",
                    "+",
                    "+        # Handlungsempfehlung",
                    "+        handlung = linkedin_aufbau.get(\"handlungsempfehlung\", {})",
                    "+        if handlung:",
                    "+            handlung_text = \"### Handlungsempfehlung:\\n\"",
                    "+            handlung_text += f\"- Stil: {handlung.get('stil', '')}\\n\"",
                    "+            if handlung.get(\"muster\"):",
                    "+                handlung_text += f\"- Muster: {'; '.join(handlung['muster'][:2])}\"",
                    "+            aufbau_sections.append(handlung_text)",
                    "+",
                    "+        # Schluss (LinkedIn style)",
                    "+        schluss = linkedin_aufbau.get(\"schluss\", {})",
                    "+        if schluss:",
                    "+            schluss_text = \"### Schluss:\\n\"",
                    "+            if schluss.get(\"soft_cta\"):",
                    "+                schluss_text += f\"- Stil: {schluss.get('soft_cta')}\\n\"",
                    "+            if schluss.get(\"muster\"):",
                    "+                schluss_text += f\"- Muster: {'; '.join(schluss['muster'][:2])}\\n\"",
                    "+            if schluss.get(\"verboten\"):",
                    "+                schluss_text += f\"- Verboten: {', '.join(schluss['verboten'])}\"",
                    "+            aufbau_sections.append(schluss_text)",
                    "+",
                    "+        sections.extend(aufbau_sections)",
                    "+",
                    "+    # Blog format: Einstieg",
                    "     einstieg = config.get(\"einstieg\", {})",
                    "     if einstieg:",
                    "         sections.append(f\"\"\"### Einstieg:"
                ]
            },
            {
                "oldStart": 192,
                "oldLines": 7,
                "newStart": 276,
                "newLines": 7,
                "lines": [
                    " - Inhaltstyp: {einstieg.get(\"inhaltstyp\", \"\")}",
                    " - Ausschluss: {einstieg.get(\"ausschluss\", \"\")}\"\"\")",
                    " ",
                    "-    # Hauptteil-Blöcke",
                    "+    # Blog format: Hauptteil-Blöcke",
                    "     hauptteil = config.get(\"hauptteil\", {})",
                    "     bloecke = hauptteil.get(\"bloecke\", [])",
                    "     if bloecke:"
                ]
            },
            {
                "oldStart": 202,
                "oldLines": 7,
                "newStart": 286,
                "newLines": 7,
                "lines": [
                    "         sections.append(f\"\"\"### Hauptteil-Struktur:",
                    " {bloecke_text}\"\"\")",
                    " ",
                    "-    # Schluss",
                    "+    # Blog format: Schluss",
                    "     schluss = config.get(\"schluss\", {})",
                    "     if schluss:",
                    "         sections.append(f\"\"\"### Schluss:"
                ]
            },
            {
                "oldStart": 210,
                "oldLines": 12,
                "newStart": 294,
                "newLines": 34,
                "lines": [
                    " - Funktion: {schluss.get(\"funktion\", \"\")}",
                    " - Abgrenzung: {schluss.get(\"abgrenzung\", \"\")}\"\"\")",
                    " ",
                    "-    # Formatierung",
                    "+    # Formatierung - handle both styles",
                    "     formatierung = config.get(\"formatierung\", {})",
                    "     if formatierung:",
                    "+        # Blog format: ausschluss array",
                    "         ausschluss = formatierung.get(\"ausschluss\", [])",
                    "         if ausschluss:",
                    "             sections.append(f\"\"\"### Formatierung verboten:",
                    " {\", \".join(ausschluss)}\"\"\")",
                    " ",
                    "+        # LinkedIn format: individual fields",
                    "+        verbote = []",
                    "+        if formatierung.get(\"emojis\") == \"verboten\" or \"verboten\" in str(formatierung.get(\"emojis\", \"\")):",
                    "+            verbote.append(\"Emojis\")",
                    "+        if formatierung.get(\"fettschrift\") == \"verboten\" or \"verboten\" in str(formatierung.get(\"fettschrift\", \"\")):",
                    "+            verbote.append(\"Fettschrift (**text**)\")",
                    "+        if formatierung.get(\"markdown\") == \"verboten\" or \"verboten\" in str(formatierung.get(\"markdown\", \"\")):",
                    "+            verbote.append(\"Markdown-Formatierung\")",
                    "+        if formatierung.get(\"hashtags\") == \"keine\":",
                    "+            verbote.append(\"Hashtags\")",
                    "+",
                    "+        if verbote and not ausschluss:  # Only add if not already handled by ausschluss",
                    "+            sections.append(f\"\"\"### Formatierung STRIKT verboten:",
                    "+{\", \".join(verbote)}\"\"\")",
                    "+",
                    "+    # Top-level verboten array (LinkedIn format)",
                    "+    verboten = config.get(\"verboten\", [])",
                    "+    if verboten:",
                    "+        sections.append(f\"\"\"### VERBOTEN (strikt einhalten!):",
                    "+- {chr(10).join(['- ' + v if not v.startswith('-') else v for v in verboten])}\"\"\")",
                    "+",
                    "     return \"\\n\\n\".join(sections), output_format, erlaubte_tags"
                ]
            }
        ],
        "userModified": false,
        "replaceAll": false
    }
}
← Vorheriger Zur Liste Nächster →