Protokoll #6644

{
    "event": "PreToolUse",
    "tool_name": "Edit",
    "tool_input": {
        "file_path": "\/opt\/scripts\/pipeline\/analyze.py",
        "old_string": "                if source and target:\n                    cursor = db.execute(\n                        \"\"\"INSERT IGNORE INTO entity_relations\n                           (source_entity_id, target_entity_id, relation_type, created_at)\n                           VALUES (%s, %s, %s, NOW())\"\"\",\n                        (source[\"id\"], target[\"id\"], rel[\"relation\"]),\n                    )\n                    db.commit()\n                    cursor.close()",
        "new_string": "                if source and target:\n                    # Store in entity_relations (raw pipeline data)\n                    cursor = db.execute(\n                        \"\"\"INSERT IGNORE INTO entity_relations\n                           (source_entity_id, target_entity_id, relation_type, created_at)\n                           VALUES (%s, %s, %s, NOW())\"\"\",\n                        (source[\"id\"], target[\"id\"], rel[\"relation\"]),\n                    )\n                    db.commit()\n                    cursor.close()\n\n                    # Store in entity_ontology (for semantic explorer)\n                    cursor = db.execute(\n                        \"\"\"INSERT IGNORE INTO entity_ontology\n                           (source_entity_id, target_entity_id, relation_type, direction,\n                            strength, source_type, source_id, created_at)\n                           VALUES (%s, %s, %s, 'unidirectional', 1.0, 'document', %s, NOW())\"\"\",\n                        (source[\"id\"], target[\"id\"], rel[\"relation\"], document_id),\n                    )\n                    db.commit()\n                    cursor.close()"
    }
}

{
    "tool_response": {
        "filePath": "\/opt\/scripts\/pipeline\/analyze.py",
        "oldString": "                if source and target:\n                    cursor = db.execute(\n                        \"\"\"INSERT IGNORE INTO entity_relations\n                           (source_entity_id, target_entity_id, relation_type, created_at)\n                           VALUES (%s, %s, %s, NOW())\"\"\",\n                        (source[\"id\"], target[\"id\"], rel[\"relation\"]),\n                    )\n                    db.commit()\n                    cursor.close()",
        "newString": "                if source and target:\n                    # Store in entity_relations (raw pipeline data)\n                    cursor = db.execute(\n                        \"\"\"INSERT IGNORE INTO entity_relations\n                           (source_entity_id, target_entity_id, relation_type, created_at)\n                           VALUES (%s, %s, %s, NOW())\"\"\",\n                        (source[\"id\"], target[\"id\"], rel[\"relation\"]),\n                    )\n                    db.commit()\n                    cursor.close()\n\n                    # Store in entity_ontology (for semantic explorer)\n                    cursor = db.execute(\n                        \"\"\"INSERT IGNORE INTO entity_ontology\n                           (source_entity_id, target_entity_id, relation_type, direction,\n                            strength, source_type, source_id, created_at)\n                           VALUES (%s, %s, %s, 'unidirectional', 1.0, 'document', %s, NOW())\"\"\",\n                        (source[\"id\"], target[\"id\"], rel[\"relation\"], document_id),\n                    )\n                    db.commit()\n                    cursor.close()",
        "originalFile": "\"\"\"\nSemantic analysis for KI-System Pipeline\nEntity extraction, taxonomy classification, ontology mapping.\n\"\"\"\n\nimport json\nimport os\nimport time\n\nimport requests\n\nfrom config import ANTHROPIC_API_KEY, ANTHROPIC_MODEL, OLLAMA_CHAT_MODEL, OLLAMA_HOST\nfrom db import db\nfrom protokoll import protokoll\n\n\ndef get_anthropic_client():\n    \"\"\"Get Anthropic API client.\"\"\"\n    try:\n        import anthropic\n\n        if ANTHROPIC_API_KEY:\n            db.log(\"INFO\", \"Using Anthropic API (Claude)\")\n            return anthropic.Anthropic(api_key=ANTHROPIC_API_KEY)\n        else:\n            db.log(\"WARNING\", \"No Anthropic API key found, falling back to Ollama\")\n    except ImportError:\n        db.log(\"WARNING\", \"anthropic package not installed, falling back to Ollama\")\n    return None\n\n\ndef extract_entities_ollama(text, model=\"gemma3:27b-it-qat\"):\n    \"\"\"Extract entities using Ollama.\"\"\"\n    # Load prompt from database\n    prompt_template = db.get_prompt(\"entity_extraction\")\n\n    if not prompt_template:\n        db.log(\"WARNING\", \"entity_extraction prompt not found in DB, using fallback\")\n        prompt_template = \"\"\"Analysiere den Text und extrahiere wichtige Entitäten.\nKategorisiere als: PERSON, ORGANIZATION, CONCEPT, LOCATION\nAntworte NUR im JSON-Format:\n{\"entities\": [{\"name\": \"...\", \"type\": \"...\", \"description\": \"...\"}]}\n\nText:\n{{TEXT}}\"\"\"\n\n    prompt = prompt_template.replace(\"{{TEXT}}\", text[:3000])\n\n    try:\n        start_time = time.time()\n        response = requests.post(\n            f\"{OLLAMA_HOST}\/api\/generate\",\n            json={\"model\": model, \"prompt\": prompt, \"stream\": False, \"format\": \"json\"},\n            timeout=120,\n        )\n        response.raise_for_status()\n        data = response.json()\n        duration_ms = int((time.time() - start_time) * 1000)\n\n        # Parse JSON from response\n        response_text = data.get(\"response\", \"{}\")\n\n        # Log to ki-protokoll\n        protokoll.log_llm_call(\n            request=f\"[entity_extraction] {prompt[:500]}...\",\n            response=response_text[:2000],\n            model_name=f\"ollama:{model}\",\n            tokens_input=data.get(\"prompt_eval_count\", 0),\n            tokens_output=data.get(\"eval_count\", 0),\n            duration_ms=duration_ms,\n            status=\"completed\",\n        )\n\n        try:\n            entities = json.loads(response_text)\n            return entities.get(\"entities\", [])\n        except json.JSONDecodeError:\n            db.log(\"WARNING\", \"Failed to parse entity JSON from Ollama\")\n            return []\n    except Exception as e:\n        db.log(\"ERROR\", f\"Ollama entity extraction failed: {e}\")\n        protokoll.log_llm_call(\n            request=f\"[entity_extraction] {prompt[:500]}...\",\n            model_name=f\"ollama:{model}\",\n            status=\"error\",\n            error_message=str(e),\n        )\n        return []\n\n\ndef extract_entities_anthropic(text, client):\n    \"\"\"Extract entities using Anthropic Claude.\"\"\"\n    # Get prompt from database\n    prompt_template = db.get_prompt(\"entity_extraction\")\n\n    if not prompt_template:\n        prompt_template = \"\"\"Analysiere den folgenden deutschen Text und extrahiere alle wichtigen Entitäten.\n\nKategorisiere jede Entität als:\n- PERSON (Namen von Personen)\n- ORGANIZATION (Firmen, Institutionen, Gruppen)\n- CONCEPT (Fachbegriffe, Methoden, Theorien)\n- LOCATION (Orte, Länder)\n- DATE (Zeitangaben)\n- OTHER (Sonstiges)\n\nAntworte NUR im JSON-Format:\n{\"entities\": [{\"name\": \"...\", \"type\": \"...\", \"context\": \"kurzer Kontext der Erwähnung\"}]}\n\nText:\n{{TEXT}}\"\"\"\n\n    prompt = prompt_template.replace(\"{{TEXT}}\", text[:4000])\n\n    try:\n        start_time = time.time()\n        message = client.messages.create(\n            model=ANTHROPIC_MODEL, max_tokens=2000, messages=[{\"role\": \"user\", \"content\": prompt}]\n        )\n        duration_ms = int((time.time() - start_time) * 1000)\n\n        response_text = message.content[0].text\n\n        # Log to ki-protokoll\n        protokoll.log_llm_call(\n            request=f\"[entity_extraction] {prompt[:500]}...\",\n            response=response_text[:2000],\n            model_name=ANTHROPIC_MODEL,\n            tokens_input=message.usage.input_tokens,\n            tokens_output=message.usage.output_tokens,\n            duration_ms=duration_ms,\n            status=\"completed\",\n        )\n\n        # Extract JSON from response\n        import re\n\n        json_match = re.search(r\"\\{[\\s\\S]*\\}\", response_text)\n        if json_match:\n            entities = json.loads(json_match.group())\n            return entities.get(\"entities\", [])\n        return []\n    except Exception as e:\n        db.log(\"ERROR\", f\"Anthropic entity extraction failed: {e}\")\n        protokoll.log_llm_call(\n            request=f\"[entity_extraction] {prompt[:500]}...\",\n            model_name=ANTHROPIC_MODEL,\n            status=\"error\",\n            error_message=str(e),\n        )\n        return []\n\n\ndef extract_relations(text, entities, client=None):\n    \"\"\"Extract relations between entities.\"\"\"\n    if not entities or len(entities) < 2:\n        return []\n\n    entity_names = [e[\"name\"] for e in entities[:20]]\n\n    # Load prompt from database\n    prompt_template = db.get_prompt(\"relation_extraction\")\n\n    if not prompt_template:\n        db.log(\"WARNING\", \"relation_extraction prompt not found in DB, using fallback\")\n        prompt_template = \"\"\"Identifiziere Beziehungen zwischen Entitäten.\nEntitäten: {{ENTITIES}}\nBeziehungstypen: DEVELOPED_BY, RELATED_TO, PART_OF, USED_IN, BASED_ON\nAntworte NUR im JSON-Format:\n{\"relations\": [{\"source\": \"...\", \"relation\": \"...\", \"target\": \"...\"}]}\n\nText:\n{{TEXT}}\"\"\"\n\n    prompt = prompt_template.replace(\"{{ENTITIES}}\", \", \".join(entity_names))\n    prompt = prompt.replace(\"{{TEXT}}\", text[:3000])\n\n    try:\n        start_time = time.time()\n        tokens_in, tokens_out = 0, 0\n        model_name = \"\"\n\n        if client:\n            message = client.messages.create(\n                model=ANTHROPIC_MODEL, max_tokens=1000, messages=[{\"role\": \"user\", \"content\": prompt}]\n            )\n            response_text = message.content[0].text\n            tokens_in = message.usage.input_tokens\n            tokens_out = message.usage.output_tokens\n            model_name = ANTHROPIC_MODEL\n        else:\n            response = requests.post(\n                f\"{OLLAMA_HOST}\/api\/generate\",\n                json={\"model\": OLLAMA_CHAT_MODEL, \"prompt\": prompt, \"stream\": False, \"format\": \"json\"},\n                timeout=120,\n            )\n            response.raise_for_status()\n            data = response.json()\n            response_text = data.get(\"response\", \"{}\")\n            tokens_in = data.get(\"prompt_eval_count\", 0)\n            tokens_out = data.get(\"eval_count\", 0)\n            model_name = f\"ollama:{OLLAMA_CHAT_MODEL}\"\n\n        duration_ms = int((time.time() - start_time) * 1000)\n\n        # Log to ki-protokoll\n        protokoll.log_llm_call(\n            request=f\"[relation_extraction] {prompt[:500]}...\",\n            response=response_text[:2000],\n            model_name=model_name,\n            tokens_input=tokens_in,\n            tokens_output=tokens_out,\n            duration_ms=duration_ms,\n            status=\"completed\",\n        )\n\n        import re\n\n        json_match = re.search(r\"\\{[\\s\\S]*\\}\", response_text)\n        if json_match:\n            data = json.loads(json_match.group())\n            return data.get(\"relations\", [])\n        return []\n    except Exception as e:\n        db.log(\"ERROR\", f\"Relation extraction failed: {e}\")\n        protokoll.log_llm_call(\n            request=f\"[relation_extraction] {prompt[:500]}...\",\n            model_name=ANTHROPIC_MODEL if client else f\"ollama:{OLLAMA_CHAT_MODEL}\",\n            status=\"error\",\n            error_message=str(e),\n        )\n        return []\n\n\ndef classify_taxonomy(text, client=None):\n    \"\"\"Classify text into taxonomy categories.\"\"\"\n    prompt_template = db.get_prompt(\"taxonomy_classification\")\n\n    if not prompt_template:\n        prompt_template = \"\"\"Klassifiziere den folgenden Text in passende Kategorien.\n\nWähle aus diesen Hauptkategorien:\n- Methoden (Therapiemethoden, Techniken)\n- Theorie (Konzepte, Modelle, Grundlagen)\n- Praxis (Anwendung, Fallbeispiele)\n- Organisation (Strukturen, Prozesse)\n- Kommunikation (Gesprächsführung, Interaktion)\n- Entwicklung (Persönliche Entwicklung, Veränderung)\n\nAntworte NUR im JSON-Format:\n{\"categories\": [\"...\", \"...\"], \"confidence\": 0.0-1.0}\n\nText:\n{{TEXT}}\"\"\"\n\n    prompt = prompt_template.replace(\"{{TEXT}}\", text[:2000])\n\n    try:\n        start_time = time.time()\n        tokens_in, tokens_out = 0, 0\n        model_name = \"\"\n\n        if client:\n            message = client.messages.create(\n                model=ANTHROPIC_MODEL, max_tokens=500, messages=[{\"role\": \"user\", \"content\": prompt}]\n            )\n            response_text = message.content[0].text\n            tokens_in = message.usage.input_tokens\n            tokens_out = message.usage.output_tokens\n            model_name = ANTHROPIC_MODEL\n        else:\n            response = requests.post(\n                f\"{OLLAMA_HOST}\/api\/generate\",\n                json={\"model\": OLLAMA_CHAT_MODEL, \"prompt\": prompt, \"stream\": False, \"format\": \"json\"},\n                timeout=60,\n            )\n            response.raise_for_status()\n            data = response.json()\n            response_text = data.get(\"response\", \"{}\")\n            tokens_in = data.get(\"prompt_eval_count\", 0)\n            tokens_out = data.get(\"eval_count\", 0)\n            model_name = f\"ollama:{OLLAMA_CHAT_MODEL}\"\n\n        duration_ms = int((time.time() - start_time) * 1000)\n\n        # Log to ki-protokoll\n        protokoll.log_llm_call(\n            request=f\"[taxonomy_classification] {prompt[:500]}...\",\n            response=response_text[:2000],\n            model_name=model_name,\n            tokens_input=tokens_in,\n            tokens_output=tokens_out,\n            duration_ms=duration_ms,\n            status=\"completed\",\n        )\n\n        import re\n\n        json_match = re.search(r\"\\{[\\s\\S]*\\}\", response_text)\n        if json_m... [TRUNCATED-7b5cd42bc4ff23c2]",
        "structuredPatch": [
            {
                "oldStart": 403,
                "oldLines": 6,
                "newStart": 403,
                "newLines": 7,
                "lines": [
                    "                 cursor.close()",
                    " ",
                    "                 if source and target:",
                    "+                    # Store in entity_relations (raw pipeline data)",
                    "                     cursor = db.execute(",
                    "                         \"\"\"INSERT IGNORE INTO entity_relations",
                    "                            (source_entity_id, target_entity_id, relation_type, created_at)"
                ]
            },
            {
                "oldStart": 411,
                "oldLines": 6,
                "newStart": 412,
                "newLines": 17,
                "lines": [
                    "                     )",
                    "                     db.commit()",
                    "                     cursor.close()",
                    "+",
                    "+                    # Store in entity_ontology (for semantic explorer)",
                    "+                    cursor = db.execute(",
                    "+                        \"\"\"INSERT IGNORE INTO entity_ontology",
                    "+                           (source_entity_id, target_entity_id, relation_type, direction,",
                    "+                            strength, source_type, source_id, created_at)",
                    "+                           VALUES (%s, %s, %s, 'unidirectional', 1.0, 'document', %s, NOW())\"\"\",",
                    "+                        (source[\"id\"], target[\"id\"], rel[\"relation\"], document_id),",
                    "+                    )",
                    "+                    db.commit()",
                    "+                    cursor.close()",
                    "             except Exception as e:",
                    "                 db.log(\"WARNING\", f\"Failed to store relation: {e}\")",
                    " "
                ]
            }
        ],
        "userModified": false,
        "replaceAll": false
    }
}