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:
somew1nd committed 2026-09-08 17:05:54 -07:00
1 parent 611d1a0947
commit a45daf23f8
120 files changed
+6301 -1710

No files matched your search

+3 -3
View File
@@ -257,7 +257,7 @@ async def test_validator_burst_success_executes_every_member(
result = await node(state)
report = result["last_execution_result"]
assert report["status"] == "success"
assert report["status"] == "dispatched"
assert report["burst"] is True
assert report["incident"] is None
assert result["open_incident"] is None
@@ -287,7 +287,7 @@ async def test_validator_success_closes_open_incident(mock_mcp, mock_context, te
with patch("artemis.utils.image_diff.check_ui_change", return_value=True):
result = await node(state)
assert result["last_execution_result"]["status"] == "success"
assert result["last_execution_result"]["status"] == "dispatched"
assert result["open_incident"] is None
# The closed record is handed over once so the Operator settles the intent.
assert result["last_closed_incident"]["kind"] == "safety_net"
@@ -805,7 +805,7 @@ async def test_validator_pre_execution_validation_ocr_direct_to_pixel(
assert "last_execution_result" in result
report = result["last_execution_result"]
assert report["status"] == "success"
assert report["status"] == "dispatched"
@pytest.mark.asyncio