feat: add agentic video analysis and clarify action results

Report device actions as dispatched and preserve full failure details. Route
Flash through McpActionExecutor and use ToolFailure across helper tools and
agent loops instead of inferring failure from response text.

Require model-provided descriptions for coordinate targets. Keep observed
element metadata separate from those descriptions in safety checks, visual
summaries, history, and frontend labels.

Add Gemini Interactions API video analysis with configurable processing mode,
chunk size, and timeouts. Centralize Google provider capabilities and token
usage normalization, and update google-genai to 2.22.0.

Preserve system instructions on follow-up interactions, replan pending chunks
when falling back to static processing, and reject unanswered native video
and audio segments instead of caching placeholder results. Keep helper-tool
failure status intact through history tools and committee calls.

Validation: 1,762 Python unit tests passed (3 skipped), 40 frontend formatter
tests passed, and the production UI build completed. Ruff lint, formatting,
the quality ratchet, and git diff checks passed.

artemis/services/llm.py

@@ -45,6 +45,7 @@ from artemis.config import (
 )
 from artemis.context import ArtemisContext
 from artemis.data_engine.trace import CURRENT_TRACE_ID, DataEngineCallbackHandler
+from artemis.llm.google import is_google_chat_model, is_google_provider
 from artemis.llm.reliability import (
     CircuitBreaker,
     FailureCategory,
@@ -550,20 +551,10 @@ class RobustChatModelWrapper:
         processed_tools = list(tools_list) if tools_list is not None else []
 
         # Determine if the underlying model provider is Google / Gemini
-        is_google_provider = False
         if self.endpoint is not None:
-            is_google_provider = self.endpoint.provider in (
-                ModelProvider.GOOGLE,
-                ModelProvider.GEMINI,
-            )
+            google_backed = is_google_provider(self.endpoint.provider)
         else:
-            base_model_cls = getattr(self.base_model, "__class__", None)
-            base_model_name = base_model_cls.__name__ if base_model_cls else ""
-            is_google_provider = (
-                "Google" in base_model_name
-                or "Gemini" in base_model_name
-                or "VertexAI" in base_model_name
-            )
+            google_backed = is_google_chat_model(self.base_model)
 
         has_explicit_google_search = any(
             isinstance(t, dict) and "google_search" in t for t in processed_tools
@@ -572,7 +563,7 @@ class RobustChatModelWrapper:
             self.endpoint is not None and self.endpoint.enable_grounding
         ) or has_explicit_google_search
 
-        if is_google_provider:
+        if google_backed:
             if should_ground:
                 # Add native Google Search Grounding tool if not already present
                 if not has_explicit_google_search: