feat(chat): replace built-in chat with LibreChat SSO integration

Replaces the custom chat page with an external LibreChat instance that
shares Keycloak SSO for seamless auto-login. Removes Tools and Knowledge
Base pages as these are now handled by LibreChat's built-in capabilities.

- Add LibreChat service to docker-compose with Ollama backend config
- Add Keycloak OIDC client (certifai-librechat) with prompt=none for
  silent SSO
- Create librechat.yaml with CERTifAI branding, Ollama endpoint, and
  custom page title/logo
- Change sidebar Chat link to external URL (opens LibreChat in new tab)
- Remove chat page, tools page, knowledge base page and all related
  components (chat_sidebar, chat_bubble, chat_input_bar, etc.)
- Remove tool_card, file_row components and tool/knowledge models
- Remove chat_stream SSE handler (no longer needed)
- Clean up i18n files: remove chat, tools, knowledge sections
- Dashboard article summarization via Ollama remains intact

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

assets/i18n/en.json

@@ -38,8 +38,6 @@
     "dashboard": "Dashboard",
     "providers": "Providers",
     "chat": "Chat",
-    "tools": "Tools",
-    "knowledge_base": "Knowledge Base",
     "developer": "Developer",
     "organization": "Organization",
     "switch_light": "Switch to light mode",
@@ -72,28 +70,6 @@
     "trending": "Trending",
     "recent_searches": "Recent Searches"
   },
-  "chat": {
-    "new_chat": "New Chat",
-    "general": "General",
-    "conversations": "Conversations",
-    "news_chats": "News Chats",
-    "all_chats": "All Chats",
-    "no_conversations": "No conversations yet",
-    "type_message": "Type a message...",
-    "model_label": "Model:",
-    "no_models": "No models available",
-    "send_to_start": "Send a message to start the conversation.",
-    "you": "You",
-    "assistant": "Assistant",
-    "thinking": "Thinking...",
-    "copy_response": "Copy last response",
-    "copy_conversation": "Copy conversation",
-    "edit_last": "Edit last message",
-    "just_now": "just now",
-    "minutes_ago": "{n}m ago",
-    "hours_ago": "{n}h ago",
-    "days_ago": "{n}d ago"
-  },
   "providers": {
     "title": "Providers",
     "subtitle": "Configure your LLM and embedding backends",
@@ -107,37 +83,6 @@
     "active_config": "Active Configuration",
     "embedding": "Embedding"
   },
-  "tools": {
-    "title": "Tools",
-    "subtitle": "Manage MCP servers and tool integrations",
-    "calculator": "Calculator",
-    "calculator_desc": "Mathematical computation and unit conversion",
-    "tavily": "Tavily Search",
-    "tavily_desc": "AI-optimized web search API for real-time information",
-    "searxng": "SearXNG",
-    "searxng_desc": "Privacy-respecting metasearch engine",
-    "file_reader": "File Reader",
-    "file_reader_desc": "Read and parse local files in various formats",
-    "code_executor": "Code Executor",
-    "code_executor_desc": "Sandboxed code execution for Python and JavaScript",
-    "web_scraper": "Web Scraper",
-    "web_scraper_desc": "Extract structured data from web pages",
-    "email_sender": "Email Sender",
-    "email_sender_desc": "Send emails via configured SMTP server",
-    "git_ops": "Git Operations",
-    "git_ops_desc": "Interact with Git repositories for version control"
-  },
-  "knowledge": {
-    "title": "Knowledge Base",
-    "subtitle": "Manage documents for RAG retrieval",
-    "search_placeholder": "Search files...",
-    "name": "Name",
-    "type": "Type",
-    "size": "Size",
-    "chunks": "Chunks",
-    "uploaded": "Uploaded",
-    "actions": "Actions"
-  },
   "developer": {
     "agents_title": "Agent Builder",
     "agents_desc": "Build and manage AI agents with LangGraph. Create multi-step reasoning pipelines, tool-using agents, and autonomous workflows.",