feat(assistant): implement tool registry and expand assistant capabilities

Introduce a centralized tool registry system for the assistant to manage
executable operations, permissions, and tool catalogs. This refactors
the assistant dispatch logic from a monolithic approach to a modular,
decorator-based registry.

Key changes:
- Implement `AssistantToolRegistry` to handle tool registration,
  permission checks, and safe operation identification.
- Add a suite of new assistant tools: backup, commit, branch creation,
  deployment, health summary, environment listing, LLM operations,
  maintenance, migration, and dashboard searching.
- Refactor `_dispatch.py` and `_llm_planner.py` to utilize the new
  registry for intent resolution and tool catalog building.
- Enhance the LLM planner to support more descriptive clarification
  responses in Russian when intents are ambiguous.
- Update the frontend to support the new tool-based workflow, including
  improved i18n labels for assistant operations and a new step-by-step
  wizard for the migration page.
- Add ADR-0008 to document the architectural decision for the tool
  registry.

backend/src/api/routes/assistant/_tool_llm_validation.py

@@ -0,0 +1,97 @@
+# #region AssistantToolLlmValidation [C:3] [TYPE Module] [SEMANTICS assistant, tool, llm, validation]
+# @BRIEF Handler for the "run_llm_validation" tool — run LLM dashboard validation.
+# @LAYER API
+# @RELATION DEPENDS_ON -> [AssistantToolRegistry]
+# @RELATION DEPENDS_ON -> [LLMProviderService]
+# @RELATION DEPENDS_ON -> [TaskManager]
+
+from __future__ import annotations
+
+from typing import Any
+
+from fastapi import HTTPException
+from sqlalchemy.orm import Session
+
+from src.core.config_manager import ConfigManager
+from src.core.logger import belief_scope, logger
+from src.core.task_manager import TaskManager
+from src.schemas.auth import User
+from src.services.llm_provider import LLMProviderService
+
+from ._resolvers import (
+    _resolve_dashboard_id_entity,
+    _resolve_env_id,
+    _resolve_provider_id,
+)
+from ._schemas import AssistantAction
+from ._tool_registry import _check_any_permission, assistant_tool
+
+
+# #region handle_run_llm_validation [C:3] [TYPE Function]
+@assistant_tool(
+    operation="run_llm_validation",
+    domain="llm",
+    description="Run LLM dashboard validation by dashboard id/slug/title",
+    optional_entities=["dashboard_ref", "environment", "provider"],
+    risk_level="guarded",
+    requires_confirmation=False,
+    permission_checks=[("plugin:llm_dashboard_validation", "EXECUTE")],
+)
+@belief_scope("run_llm_validation")
+async def handle_run_llm_validation(
+    intent: dict[str, Any],
+    current_user: User,
+    task_manager: TaskManager,
+    config_manager: ConfigManager,
+    db: Session,
+) -> tuple[str, str | None, list[AssistantAction]]:
+    """Run LLM dashboard validation."""
+    _check_any_permission(current_user, [("plugin:llm_dashboard_validation", "EXECUTE")])
+    entities = intent.get("entities", {})
+    env_token = entities.get("environment")
+    env_id = _resolve_env_id(env_token, config_manager) or _resolve_env_id(
+        None, config_manager
+    )
+    dashboard_id = _resolve_dashboard_id_entity(
+        entities, config_manager, env_hint=env_token
+    )
+    provider_id = _resolve_provider_id(
+        entities.get("provider"),
+        db,
+        config_manager=config_manager,
+        task_key="dashboard_validation",
+    )
+    if not dashboard_id or not env_id or (not provider_id):
+        raise HTTPException(
+            status_code=422,
+            detail="Missing dashboard_id/environment/provider. Укажите ID/slug дашборда или окружение.",
+        )
+    provider = LLMProviderService(db).get_provider(provider_id)
+    if not provider or not bool(provider.is_multimodal):
+        raise HTTPException(
+            status_code=422,
+            detail="Selected provider model is not multimodal for dashboard validation. Выберите мультимодальную модель (например, gpt-4o).",
+        )
+    task = await task_manager.create_task(
+        plugin_id="llm_dashboard_validation",
+        params={
+            "dashboard_id": str(dashboard_id),
+            "environment_id": env_id,
+            "provider_id": provider_id,
+        },
+        user_id=current_user.id,
+    )
+    return (
+        f"LLM-валидация запущена. task_id={task.id}",
+        task.id,
+        [
+            AssistantAction(type="open_task", label="Open Task", target=task.id),
+            AssistantAction(
+                type="open_reports", label="Open Reports", target="/reports"
+            ),
+        ],
+    )
+
+
+# #endregion handle_run_llm_validation
+# #endregion AssistantToolLlmValidation