chore: remove deprecated Docker Compose and entrypoint scripts; add Bandit for security checks

src/datacenter_docs/api/main.py

@@ -348,6 +348,7 @@ async def trigger_proxmox_documentation() -> Dict[str, Any]:
     Returns job_id for status monitoring
     """
     from celery import Celery
+
     from datacenter_docs.utils.config import get_settings
 
     try:
@@ -388,6 +389,7 @@ async def get_job_status(job_id: str) -> Dict[str, Any]:
     Returns current status and progress information
     """
     from celery.result import AsyncResult
+
     from datacenter_docs.workers.celery_app import celery_app
 
     try:
@@ -441,24 +443,25 @@ async def list_documentation_files() -> Dict[str, Any]:
 
             for file_path in category_dir.glob("*.md"):
                 stat = file_path.stat()
-                files.append({
-                    "filename": file_path.name,
-                    "size": stat.st_size,
-                    "modified": stat.st_mtime,
-                    "path": f"{category}/{file_path.name}"
-                })
+                files.append(
+                    {
+                        "filename": file_path.name,
+                        "size": stat.st_size,
+                        "modified": stat.st_mtime,
+                        "path": f"{category}/{file_path.name}",
+                    }
+                )
 
             if files:
-                files_by_category[category] = sorted(files, key=lambda x: x["modified"], reverse=True)
+                files_by_category[category] = sorted(
+                    files, key=lambda x: x["modified"], reverse=True
+                )
 
     total_files = sum(len(files) for files in files_by_category.values())
 
     return {
-        "categories": [
-            {"name": cat, "files": files}
-            for cat, files in files_by_category.items()
-        ],
-        "total": total_files
+        "categories": [{"name": cat, "files": files} for cat, files in files_by_category.items()],
+        "total": total_files,
     }
 
 
@@ -495,7 +498,7 @@ async def get_documentation_content(category: str, filename: str) -> Dict[str, A
             "category": category,
             "content": content,
             "size": stat.st_size,
-            "modified": stat.st_mtime
+            "modified": stat.st_mtime,
         }
     except Exception as e:
         logger.error(f"Failed to read file {file_path}: {e}")
@@ -513,38 +516,21 @@ async def get_job_logs(job_id: str, tail: int = 100) -> Dict[str, Any]:
 
     try:
         # Get worker logs and filter for job_id
-        cmd = [
-            "docker",
-            "logs",
-            "datacenter-docs-worker-dev",
-            "--tail",
-            str(tail)
-        ]
+        cmd = ["docker", "logs", "datacenter-docs-worker-dev", "--tail", str(tail)]
 
-        result = subprocess.run(
-            cmd,
-            capture_output=True,
-            text=True,
-            timeout=5
-        )
+        result = subprocess.run(cmd, capture_output=True, text=True, timeout=5)
 
         all_logs = result.stdout + result.stderr
 
         # Filter logs containing the job_id
         job_logs = [
-            line
-            for line in all_logs.split("\n")
-            if job_id in line or "ForkPoolWorker" in line
+            line for line in all_logs.split("\n") if job_id in line or "ForkPoolWorker" in line
         ]
 
         # Take last 50 relevant lines
         relevant_logs = job_logs[-50:] if len(job_logs) > 50 else job_logs
 
-        return {
-            "job_id": job_id,
-            "logs": relevant_logs,
-            "total_lines": len(relevant_logs)
-        }
+        return {"job_id": job_id, "logs": relevant_logs, "total_lines": len(relevant_logs)}
 
     except subprocess.TimeoutExpired:
         raise HTTPException(status_code=504, detail="Timeout getting logs")

src/datacenter_docs/chat/agent.py

@@ -8,10 +8,10 @@ from datetime import datetime
 from pathlib import Path
 from typing import Any, Dict, List, Optional
 
-from langchain_community.embeddings import HuggingFaceEmbeddings
-from langchain_community.vectorstores import Chroma
 from langchain.schema import Document
 from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_community.vectorstores import Chroma
 
 from ..mcp.client import MCPClient
 from ..utils.llm_client import LLMClient
@@ -48,7 +48,9 @@ class DocumentationAgent:
         self.vector_store: Optional[Chroma] = None
 
         try:
-            self.embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
+            self.embeddings = HuggingFaceEmbeddings(
+                model_name="sentence-transformers/all-MiniLM-L6-v2"
+            )
             self._load_vector_store()
             logger.info("Vector store initialized successfully")
         except Exception as e:
@@ -136,7 +138,9 @@ class DocumentationAgent:
             logger.info(f"💾 Adding {len(documents)} chunks to vector store...")
             self.vector_store.add_documents(documents)
             self.vector_store.persist()
-            logger.info(f"✅ Indexed {files_processed} files ({len(documents)} chunks) from documentation")
+            logger.info(
+                f"✅ Indexed {files_processed} files ({len(documents)} chunks) from documentation"
+            )
         else:
             logger.warning("⚠️  No documents to index")
 
@@ -191,7 +195,9 @@ class DocumentationAgent:
                         "last_updated": doc.metadata.get("indexed_at", ""),
                     }
                 )
-                logger.info(f"  ✓ Section: {doc.metadata.get('section')} (relevance: {relevance_score*100:.1f}%, distance: {score:.3f})")
+                logger.info(
+                    f"  ✓ Section: {doc.metadata.get('section')} (relevance: {relevance_score*100:.1f}%, distance: {score:.3f})"
+                )
 
             return formatted_results
 
@@ -342,7 +348,7 @@ Respond in JSON format:
                 "de": "German",
                 "pt": "Portuguese",
                 "zh": "Chinese",
-                "ja": "Japanese"
+                "ja": "Japanese",
             }
 
             language_instruction = ""

src/datacenter_docs/chat/main.py

@@ -2,7 +2,6 @@
 Chat server with Socket.IO support for real-time communication.
 """
 
-import asyncio
 import logging
 from pathlib import Path
 from typing import Any, Dict
@@ -36,9 +35,7 @@ async def index_documentation_if_needed() -> None:
         try:
             # Create temporary agent for indexing
             temp_agent = DocumentationAgent(
-                mcp_client=None,
-                llm_client=None,
-                vector_store_path=str(vector_store_path)
+                mcp_client=None, llm_client=None, vector_store_path=str(vector_store_path)
             )
 
             # Index documentation
@@ -77,6 +74,7 @@ async def initialize_agent() -> None:
         logger.warning(f"Failed to initialize Documentation Agent: {e}")
         agent = None
 
+
 # Create Socket.IO server
 # Using async_mode="asgi" for FastAPI integration
 # python-socketio 5.x automatically supports Engine.IO v4 for socket.io-client 4.x compatibility
@@ -202,7 +200,9 @@ async def chat(sid: str, data: Dict[str, Any]) -> None:
             )
 
             response = {
-                "message": ai_response.get("message", "I apologize, I couldn't generate a response."),
+                "message": ai_response.get(
+                    "message", "I apologize, I couldn't generate a response."
+                ),
                 "type": "bot",
                 "timestamp": data.get("timestamp"),
                 "related_docs": ai_response.get("related_docs", []),

src/datacenter_docs/collectors/proxmox_collector.py

@@ -50,9 +50,7 @@ class ProxmoxCollector(BaseCollector):
 
             # Check if we have real Proxmox credentials configured
             if not settings.PROXMOX_HOST or settings.PROXMOX_HOST == "proxmox.example.com":
-                self.logger.warning(
-                    "Proxmox host not configured, using mock data for development"
-                )
+                self.logger.warning("Proxmox host not configured, using mock data for development")
                 self.connected = True
                 return True
 
@@ -312,10 +310,14 @@ class ProxmoxCollector(BaseCollector):
                     nodes = self.proxmox_client.nodes.get()
                     if nodes:
                         node_name = nodes[0]["node"]  # Use first node for storage info
-                        status = self.proxmox_client.nodes(node_name).storage(storage_id).status.get()
+                        status = (
+                            self.proxmox_client.nodes(node_name).storage(storage_id).status.get()
+                        )
                         store.update(status)
                 except Exception as e:
-                    self.logger.warning(f"Failed to get detailed info for storage {storage_id}: {e}")
+                    self.logger.warning(
+                        f"Failed to get detailed info for storage {storage_id}: {e}"
+                    )
 
             self.logger.info(f"Collected {len(storage)} storage pools")
             return storage
@@ -354,7 +356,9 @@ class ProxmoxCollector(BaseCollector):
                     self.logger.warning(f"Failed to get networks from node {node_name}: {e}")
                     continue
 
-            self.logger.info(f"Collected {len(networks)} network interfaces from {len(nodes)} nodes")
+            self.logger.info(
+                f"Collected {len(networks)} network interfaces from {len(nodes)} nodes"
+            )
             return networks
 
         except Exception as e:

src/datacenter_docs/generators/template_generator.py

@@ -88,9 +88,7 @@ class TemplateBasedGenerator(BaseGenerator):
             template_path: Path to YAML template file
         """
         self.template = DocumentationTemplate(Path(template_path))
-        super().__init__(
-            name=self.template.collector, section=f"{self.template.collector}_docs"
-        )
+        super().__init__(name=self.template.collector, section=f"{self.template.collector}_docs")
 
     async def generate(self, data: Dict[str, Any]) -> str:
         """
@@ -104,9 +102,7 @@ class TemplateBasedGenerator(BaseGenerator):
         Returns:
             Combined documentation (all sections)
         """
-        self.logger.info(
-            f"Generating documentation for {self.template.name} using template"
-        )
+        self.logger.info(f"Generating documentation for {self.template.name} using template")
 
         # Validate data matches template collector
         collector_name = data.get("metadata", {}).get("collector", "")
@@ -140,7 +136,6 @@ class TemplateBasedGenerator(BaseGenerator):
         Returns:
             Generated section content in Markdown
         """
-        section_id = section_def.get("id", "unknown")
         section_title = section_def.get("title", "Untitled Section")
         data_requirements = section_def.get("data_requirements", [])
         prompt_template = section_def.get("prompt_template", "")
@@ -549,13 +544,15 @@ Guidelines:
 
             except Exception as e:
                 self.logger.error(f"Failed to generate section for {loop_over} item {idx}: {e}")
-                results.append({
-                    "section_id": f"{section_id}_item_{idx}",
-                    "success": False,
-                    "error": str(e),
-                    "item_index": idx,
-                    "total_items": total_items,
-                })
+                results.append(
+                    {
+                        "section_id": f"{section_id}_item_{idx}",
+                        "success": False,
+                        "error": str(e),
+                        "item_index": idx,
+                        "total_items": total_items,
+                    }
+                )
 
         return results
 

src/datacenter_docs/utils/llm_client.py

@@ -84,9 +84,7 @@ class LLMClient:
         # Increased timeout to 120s for documentation generation (large prompts)
         http_client = httpx.AsyncClient(verify=False, timeout=120.0)
         self.client = AsyncOpenAI(
-            base_url=self.base_url,
-            api_key=self.api_key,
-            http_client=http_client
+            base_url=self.base_url, api_key=self.api_key, http_client=http_client
         )
 
         logger.info(f"Initialized LLM client: base_url={self.base_url}, model={self.model}")

src/datacenter_docs/workers/documentation_tasks.py

@@ -8,7 +8,7 @@ from infrastructure systems (Proxmox, VMware, Kubernetes, etc.)
 import logging
 from datetime import datetime
 from pathlib import Path
-from typing import Any, Dict, List
+from typing import Any, Dict
 
 from celery import group
 
@@ -18,9 +18,7 @@ logger = logging.getLogger(__name__)
 
 
 @celery_app.task(name="collect_and_generate_docs", bind=True)
-def collect_and_generate_docs(
-    self, collector_name: str, template_path: str
-) -> Dict[str, Any]:
+def collect_and_generate_docs(self, collector_name: str, template_path: str) -> Dict[str, Any]:
     """
     Collect data from infrastructure and generate documentation
 
@@ -80,9 +78,7 @@ def collect_and_generate_docs(
     return result
 
 
-async def _async_collect_and_generate(
-    collector_name: str, template_path: str
-) -> Dict[str, Any]:
+async def _async_collect_and_generate(collector_name: str, template_path: str) -> Dict[str, Any]:
     """
     Async implementation of collect and generate workflow
 
@@ -93,8 +89,8 @@ async def _async_collect_and_generate(
     Returns:
         Generation result
     """
-    from datacenter_docs.generators.template_generator import TemplateBasedGenerator
     from datacenter_docs.chat.agent import DocumentationAgent
+    from datacenter_docs.generators.template_generator import TemplateBasedGenerator
 
     # Import appropriate collector
     collector = await _get_collector(collector_name)
@@ -190,8 +186,8 @@ def generate_proxmox_docs(self) -> Dict[str, Any]:
 
     # Update task state
     self.update_state(
-        state='PROGRESS',
-        meta={'current': 0, 'total': 6, 'status': 'Starting Proxmox documentation generation...'}
+        state="PROGRESS",
+        meta={"current": 0, "total": 6, "status": "Starting Proxmox documentation generation..."},
     )
 
     template_path = "templates/documentation/proxmox.yaml"
@@ -237,10 +233,7 @@ def generate_proxmox_docs(self) -> Dict[str, Any]:
         result["completed_at"] = datetime.now().isoformat()
         logger.error(f"[{task_id}] Proxmox documentation generation failed: {e}", exc_info=True)
 
-        self.update_state(
-            state='FAILURE',
-            meta={'error': str(e), 'status': f'Failed: {str(e)}'}
-        )
+        self.update_state(state="FAILURE", meta={"error": str(e), "status": f"Failed: {str(e)}"})
 
         raise
 
@@ -267,10 +260,7 @@ def generate_all_docs() -> Dict[str, Any]:
 
     # Create parallel tasks
     task_group = group(
-        [
-            collect_and_generate_docs.s(system["collector"], system["template"])
-            for system in systems
-        ]
+        [collect_and_generate_docs.s(system["collector"], system["template"]) for system in systems]
     )
 
     # Execute group
@@ -377,11 +367,8 @@ def full_docs_pipeline() -> Dict[str, Any]:
     """
     logger.info("Starting full documentation pipeline")
 
-    # Step 1: Generate all documentation
-    generate_result = generate_all_docs()
-
-    # Step 2: Wait a bit for generation to complete, then index
-    # (In production, this would use Celery chains/chords for better coordination)
+    # Step 1: Generate all documentation, then index
+    # Use Celery chain for proper task coordination
     from celery import chain
 
     pipeline = chain(