feat(assistant): add multi-dialog UX, task-aware llm settings, and i18n cleanup

backend/src/plugins/llm_analysis/plugin.py

@@ -25,6 +25,7 @@ from ...models.llm import ValidationRecord
 from ...core.task_manager.context import TaskContext
 from ...services.llm_prompt_templates import (
     DEFAULT_LLM_PROMPTS,
+    is_multimodal_model,
     normalize_llm_settings,
     render_prompt,
 )
@@ -108,6 +109,10 @@ class DashboardValidationPlugin(PluginBase):
                 llm_log.debug(f"  Base URL: {db_provider.base_url}")
                 llm_log.debug(f"  Default Model: {db_provider.default_model}")
                 llm_log.debug(f"  Is Active: {db_provider.is_active}")
+                if not is_multimodal_model(db_provider.default_model):
+                    raise ValueError(
+                        "Dashboard validation requires a multimodal model (image input support)."
+                    )
                 
                 api_key = llm_service.get_decrypted_api_key(provider_id)
                 llm_log.debug(f"API Key decrypted (first 8 chars): {api_key[:8] if api_key and len(api_key) > 8 else 'EMPTY_OR_NONE'}...")