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/memory/chunking.py

@@ -39,6 +39,7 @@ from uuid import uuid4
 
 from langchain_core.messages import BaseMessage, HumanMessage, SystemMessage
 
+from artemis.llm.google import is_google_provider
 from artemis.memory.step_memory import JobKey, StepLens, StepMemoryService
 from artemis.memory.transcript import format_session_offset
 from artemis.utils.logger import get_logger
@@ -80,9 +81,7 @@ def _result_phrase(result: Any) -> str:
     if detail:
         return detail
     status = result.get("status")
-    if status == "success":
-        return "executed"
-    return str(status) if status else "executed"
+    return str(status) if status else "dispatched"
 
 
 def _action_phrase(step: dict) -> str:
@@ -963,7 +962,7 @@ class HistoryChunkManager:
             fallback = getattr(getattr(llm_cfg, "summarizer", None), "fallback", None)
             provider = str(getattr(fallback, "provider", "") or "")
             model = getattr(fallback, "model", None)
-            if model and provider in ("google", "gemini") and model != self._model_name:
+            if model and is_google_provider(provider) and model != self._model_name:
                 return str(model)
         except Exception as exc:
             logger.debug(f"Capsule fallback model resolution skipped: {exc}", exc_info=True)

artemis/memory/transcript.py

@@ -367,8 +367,8 @@ class TranscriptLedger:
             try:
                 from artemis.utils.task_tree import format_result_clean
 
-                # format_result_clean reports only errors/repairs; success
-                # renders as the bare status line.
+                # format_result_clean reports only errors/repairs; a dispatched
+                # action renders as the bare status line.
                 detail = format_result_clean(result)
             except Exception:
                 detail = None