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.
This commit is contained in:
1 parent
611d1a0947
commit
a45daf23f8
120 files changed
+6301
-1710
No files matched your search
@@ -18,6 +18,7 @@ from typing import Any
|
||||
from langchain_core.tools import BaseTool
|
||||
from pydantic import BaseModel
|
||||
|
||||
from artemis.core.tool_failure import ToolFailure
|
||||
from artemis.context import ArtemisContext
|
||||
from artemis.data_engine.trace import trace_langchain_tool
|
||||
from artemis.drivers.base import BaseDeviceDriver
|
||||
@@ -75,16 +76,18 @@ class GetUiHierarchyTool(ArtemisTool):
|
||||
xml_hierarchy = getattr(screen_data, "ui_hierarchy_xml", None)
|
||||
if xml_hierarchy:
|
||||
return str(xml_hierarchy)
|
||||
return "Error retrieving UI hierarchy: No UI hierarchy in screen data."
|
||||
return ToolFailure("Error retrieving UI hierarchy: No UI hierarchy in screen data.")
|
||||
if driver is not None and hasattr(driver, "get_ui_hierarchy"):
|
||||
xml_hierarchy = await driver.get_ui_hierarchy()
|
||||
if inspect.iscoroutine(xml_hierarchy):
|
||||
xml_hierarchy = await xml_hierarchy
|
||||
return str(xml_hierarchy)
|
||||
return "Error retrieving UI hierarchy: No UI Automator client or driver provided."
|
||||
return ToolFailure(
|
||||
"Error retrieving UI hierarchy: No UI Automator client or driver provided."
|
||||
)
|
||||
except Exception as e: # pylint: disable=broad-exception-caught
|
||||
logger.error(f"Failed to get UI hierarchy: {e}")
|
||||
return f"Error retrieving UI hierarchy: {e}"
|
||||
return ToolFailure(f"Error retrieving UI hierarchy: {e}")
|
||||
|
||||
|
||||
# Universal tool instance & aliases
|
||||
|
||||
Reference in new issue
Block a user