somew1nd
a45daf23f8
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.
51 lines
1.9 KiB
Python
51 lines
1.9 KiB
Python
"""The ``attempts`` marker contract between the Validator and the renderers.
|
|
|
|
The Validator writes ``"Dispatched"`` as the terminal attempt of an action the
|
|
device accepted (kept only when a retry preceded it); every failed attempt keeps
|
|
its error text. The renderers must read a retried-then-dispatched action as a
|
|
clean dispatch, never as a failure.
|
|
"""
|
|
|
|
from artemis.utils.task_tree import (
|
|
_burst_member_status,
|
|
failed_execution_error,
|
|
format_result_clean,
|
|
)
|
|
|
|
|
|
def _report(attempts: list[str], status: str = "dispatched") -> dict:
|
|
return {
|
|
"status": status,
|
|
"execution": [
|
|
{"action": "tap", "normalized_coordinates": [500, 500], "attempts": attempts}
|
|
],
|
|
}
|
|
|
|
|
|
def test_retried_then_dispatched_action_is_not_a_failure():
|
|
report = _report(["Error: tap rejected", "Dispatched"])
|
|
assert failed_execution_error(report) is None
|
|
assert format_result_clean(report) is None
|
|
|
|
|
|
def test_terminal_failure_keeps_every_attempt():
|
|
report = _report(["Error: tap rejected", "Error: tap rejected again"], status="failed")
|
|
assert failed_execution_error(report) == "Error: tap rejected | Error: tap rejected again"
|
|
assert format_result_clean(report) == "Error: tap rejected | Error: tap rejected again"
|
|
|
|
|
|
def test_burst_member_labels_follow_the_dispatch_vocabulary():
|
|
report = {
|
|
"status": "failed",
|
|
"execution": [
|
|
{"action": "tap"},
|
|
{"action": "tap", "attempts": ["Error: boom"]},
|
|
{"action": "tap", "attempts": ["Skipped (burst aborted)"]},
|
|
],
|
|
}
|
|
assert _burst_member_status(report, 0) == " (dispatched)"
|
|
assert _burst_member_status(report, 1) == " (FAILED: Error: boom)"
|
|
assert _burst_member_status(report, 2) == " (skipped)"
|
|
assert _burst_member_status(report, 3) == " (not dispatched)"
|
|
assert _burst_member_status({"execution": [{"attempts": ["Dispatched"]}]}, 0) == " (dispatched)"
|