Files
cleveragents-core/robot/helper_automation_profile_cli.py
CoreRasurae 007af498b8 refactor(autonomy): rename automation profile task flags to spec names
Renamed all 11 task-type confidence threshold fields in AutomationProfile
from phase-transition semantics to spec-defined task-type semantics.
Updated all 8 built-in profiles, CLI formatting, YAML schema, services,
and all Behave/Robot tests referencing the old field names.

Post-review fixes:
- Fixed 24 stale old field names in M6 fixture files
  (automation_profiles.json, autonomy_guardrails.json)
- Added model_validator(mode='before') to detect legacy field names
  and raise actionable ValueError with rename mapping
- Added semantic bridge comments in PlanLifecycleService mapping
  task-type thresholds to phase-transition gates
- Added threshold_field to structured log messages for observability
- Restored categorised CLI automation-profile show output to match
  spec (Phase Transitions / Decision Automation / Self-Repair /
  Execution Controls) instead of flat list
- Added missing access_network field to spec show output examples
  (Rich, Plain, JSON, YAML variants)
- Aligned ADR-017 profile fields table to all 11 fields with
  descriptions matching spec Automatable Tasks table
- Aligned automation_profiles.md threshold descriptions with spec
- Added spec section references in phase_reversion.md, error_recovery.md,
  and plan_execute.md for field naming context
- Extended repository roundtrip test to assert all 11 threshold fields
- Fixed benchmark _make_profile() passing safety fields as top-level
  kwargs instead of via SafetyProfile sub-model (incompatible with
  extra="forbid")
- Aligned CLI JSON/YAML output structure for automation-profile show
  with the specification grouped format (phase_transitions,
  decision_automation, self_repair, execution_controls)
- Moved safety boolean fields into the Execution Controls section
  of Rich output per spec examples
- Reverted auto profile description to "Fully automatic except apply"
  per specification (line 16703, line 28406)
- Improved bridge comments in test steps with semantic context for
  threshold-to-gate mappings

ISSUES CLOSED: #902
2026-03-30 13:18:07 +01:00

236 lines
7.5 KiB
Python

#!/usr/bin/env python3
"""Robot Framework helper for automation-profile CLI smoke tests.
Invoked by Robot tests to exercise the automation-profile CLI commands
in isolation using the Typer CliRunner with a per-test in-memory SQLite
database, fully isolated for parallel execution.
The module-level ``_get_service()`` in the production code calls
``get_container()`` which requires full DI wiring. We monkey-patch it
to return an ``AutomationProfileService`` backed by a fresh in-memory
SQLite ``AutomationProfileRepository`` so the tests can run without
container setup and without colliding across pabot workers.
"""
from __future__ import annotations
import json
import logging
import os
import sys
import tempfile
from pathlib import Path
from unittest.mock import patch
# Ensure the local source tree is importable
_SRC = str(Path(__file__).resolve().parents[1] / "src")
if _SRC not in sys.path:
sys.path.insert(0, _SRC)
# Suppress debug-level structlog/retry noise that pollutes stdout in the
# CliRunner capture buffer. Must happen before any cleveragents imports
# that configure structlog.
logging.getLogger().setLevel(logging.WARNING)
from sqlalchemy import create_engine # noqa: E402
from sqlalchemy.orm import sessionmaker # noqa: E402
from typer.testing import CliRunner # noqa: E402
import cleveragents.cli.commands.automation_profile as _ap_mod # noqa: E402
from cleveragents.application.services.automation_profile_service import ( # noqa: E402
AutomationProfileService,
)
from cleveragents.infrastructure.database.models import Base # noqa: E402
from cleveragents.infrastructure.database.repositories import ( # noqa: E402
AutomationProfileRepository,
)
profile_app = _ap_mod.app
_runner = CliRunner()
_VALID_YAML = """\
name: acme/robot-test
description: Robot test profile
schema_version: "1.0"
decompose_task: 0.8
create_tool: 0.7
select_tool: 1.0
edit_code: 0.6
execute_command: 0.8
create_file: 0.7
delete_content: 0.8
access_network: 0.9
install_dependency: 0.7
modify_config: 0.0
approve_plan: 0.6
safety:
require_sandbox: true
require_checkpoints: true
allow_unsafe_tools: false
"""
def _extract_json(text: str) -> object:
"""Extract and parse the first valid JSON object or array from *text*.
``format_output`` writes JSON directly to ``sys.stdout`` which the
CliRunner captures. Structlog debug messages may precede the JSON
payload. This function scans for the first ``{`` or ``[`` and
parses from there.
"""
for i, ch in enumerate(text):
if ch in ("{", "["):
try:
return json.loads(text[i:])
except json.JSONDecodeError:
continue
raise ValueError(f"No valid JSON found in output:\n{text[:500]}")
def _make_isolated_service() -> AutomationProfileService:
"""Create a fully isolated AutomationProfileService with an in-memory DB."""
engine = create_engine("sqlite:///:memory:", echo=False)
Base.metadata.create_all(engine)
factory = sessionmaker(bind=engine, expire_on_commit=False)
repo = AutomationProfileRepository(session_factory=factory, auto_commit=True)
return AutomationProfileService(repo=repo)
# Module-level service instance that is reset before each test.
_isolated_service: AutomationProfileService | None = None
def _get_service_override() -> AutomationProfileService:
"""Replacement for ``_ap_mod._get_service`` that returns the test service."""
assert _isolated_service is not None, "Call _reset_service() first"
return _isolated_service
def _reset_service() -> None:
"""Create a fresh isolated service for the next test."""
global _isolated_service
_isolated_service = _make_isolated_service()
def _invoke(args: list[str]):
"""Invoke the profile CLI with the patched service."""
with patch.object(_ap_mod, "_get_service", _get_service_override):
return _runner.invoke(profile_app, args)
def test_add_profile() -> None:
"""Test adding a profile via YAML config."""
_reset_service()
fd, path = tempfile.mkstemp(suffix=".yaml")
try:
with os.fdopen(fd, "w") as fh:
fh.write(_VALID_YAML)
result = _invoke(["add", "--config", path])
assert result.exit_code == 0, f"add failed: {result.output}"
print("add-profile-ok")
finally:
Path(path).unlink(missing_ok=True)
def test_show_profile() -> None:
"""Test showing a built-in profile."""
_reset_service()
result = _invoke(["show", "manual"])
assert result.exit_code == 0, f"show failed: {result.output}"
assert "manual" in result.output
print("show-profile-ok")
def test_show_json() -> None:
"""Test showing a profile in JSON format."""
_reset_service()
result = _invoke(["show", "manual", "--format", "json"])
assert result.exit_code == 0, f"show json failed: {result.output}"
parsed = _extract_json(result.output)
assert isinstance(parsed, dict)
assert parsed["name"] == "manual"
print("show-json-ok")
def test_show_yaml() -> None:
"""Test showing a profile in YAML format."""
_reset_service()
result = _invoke(["show", "manual", "--format", "yaml"])
assert result.exit_code == 0, f"show yaml failed: {result.output}"
assert "name: manual" in result.output
print("show-yaml-ok")
def test_list_profiles() -> None:
"""Test listing all profiles."""
_reset_service()
result = _invoke(["list"])
assert result.exit_code == 0, f"list failed: {result.output}"
assert "manual" in result.output
print("list-profiles-ok")
def test_list_json() -> None:
"""Test listing profiles in JSON format."""
_reset_service()
result = _invoke(["list", "--format", "json"])
assert result.exit_code == 0, f"list json failed: {result.output}"
parsed = _extract_json(result.output)
assert isinstance(parsed, list)
assert len(parsed) >= 8 # At least 8 built-in profiles
print("list-json-ok")
def test_remove_profile() -> None:
"""Test removing a custom profile."""
_reset_service()
# First add a profile
fd, path = tempfile.mkstemp(suffix=".yaml")
try:
with os.fdopen(fd, "w") as fh:
fh.write(_VALID_YAML)
add_result = _invoke(["add", "--config", path])
assert add_result.exit_code == 0, f"add failed: {add_result.output}"
finally:
Path(path).unlink(missing_ok=True)
# Then remove it (reuse same service so the profile persists)
result = _invoke(["remove", "acme/robot-test", "--yes"])
assert result.exit_code == 0, f"remove failed: {result.output}"
assert "removed" in result.output.lower()
print("remove-profile-ok")
def test_remove_builtin_fails() -> None:
"""Test that removing a built-in profile fails."""
_reset_service()
result = _invoke(["remove", "manual", "--yes"])
assert result.exit_code != 0, f"remove should have failed: {result.output}"
print("remove-builtin-fails-ok")
if __name__ == "__main__":
command = sys.argv[1] if len(sys.argv) > 1 else "all"
tests = {
"add": test_add_profile,
"show": test_show_profile,
"show-json": test_show_json,
"show-yaml": test_show_yaml,
"list": test_list_profiles,
"list-json": test_list_json,
"remove": test_remove_profile,
"remove-builtin-fails": test_remove_builtin_fails,
}
if command == "all":
for _name, test_fn in tests.items():
test_fn()
print("all-tests-ok")
elif command in tests:
tests[command]()
else:
print(f"Unknown test: {command}", file=sys.stderr)
sys.exit(1)