007af498b8
CI / benchmark-publish (pull_request) Has been skipped
CI / build (pull_request) Successful in 17s
CI / helm (pull_request) Successful in 33s
CI / lint (pull_request) Successful in 3m42s
CI / security (pull_request) Successful in 4m8s
CI / quality (pull_request) Successful in 4m9s
CI / typecheck (pull_request) Successful in 4m20s
CI / integration_tests (pull_request) Successful in 7m2s
CI / unit_tests (pull_request) Successful in 7m55s
CI / docker (pull_request) Successful in 1m19s
CI / coverage (pull_request) Successful in 8m46s
CI / e2e_tests (pull_request) Successful in 16m1s
CI / status-check (pull_request) Successful in 1s
CI / build (push) Successful in 17s
CI / helm (push) Successful in 22s
CI / quality (push) Successful in 31s
CI / lint (push) Successful in 3m28s
CI / typecheck (push) Successful in 3m54s
CI / benchmark-regression (push) Has been skipped
CI / security (push) Successful in 4m5s
CI / integration_tests (push) Successful in 6m13s
CI / unit_tests (push) Successful in 6m28s
CI / docker (push) Successful in 1m34s
CI / coverage (push) Successful in 12m5s
CI / e2e_tests (push) Successful in 18m47s
CI / status-check (push) Successful in 1s
CI / benchmark-publish (push) Successful in 28m0s
CI / benchmark-regression (pull_request) Successful in 59m48s
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
237 lines
7.5 KiB
Python
237 lines
7.5 KiB
Python
"""Helper script for Robot Framework semantic escalation tests."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
sys.path.insert(0, str(Path(__file__).resolve().parents[1] / "src"))
|
|
|
|
from cleveragents.application.services.autonomy_controller import (
|
|
AutonomyController,
|
|
)
|
|
from cleveragents.domain.models.core.automation_profile import (
|
|
BUILTIN_PROFILES,
|
|
AutomationProfile,
|
|
)
|
|
from cleveragents.domain.models.core.escalation import (
|
|
ConfidenceFactors,
|
|
HistoricalOutcome,
|
|
OperationContext,
|
|
)
|
|
|
|
|
|
def _test_confidence_high() -> None:
|
|
"""All positive factors produce high confidence."""
|
|
ctrl = AutonomyController()
|
|
factors = ConfidenceFactors(
|
|
past_success_rate=1.0,
|
|
codebase_familiarity=1.0,
|
|
risk_assessment=0.0,
|
|
invariant_complexity=0.0,
|
|
)
|
|
score = ctrl.compute_confidence(factors)
|
|
assert abs(score - 1.0) < 1e-6, f"Expected 1.0, got {score}"
|
|
print("confidence-high-ok")
|
|
|
|
|
|
def _test_confidence_low() -> None:
|
|
"""All negative factors produce zero confidence."""
|
|
ctrl = AutonomyController()
|
|
factors = ConfidenceFactors(
|
|
past_success_rate=0.0,
|
|
codebase_familiarity=0.0,
|
|
risk_assessment=1.0,
|
|
invariant_complexity=1.0,
|
|
)
|
|
score = ctrl.compute_confidence(factors)
|
|
assert abs(score - 0.0) < 1e-6, f"Expected 0.0, got {score}"
|
|
print("confidence-low-ok")
|
|
|
|
|
|
def _test_threshold_proceed() -> None:
|
|
"""Proceed when confidence >= threshold."""
|
|
ctrl = AutonomyController()
|
|
profile = AutomationProfile(name="test", create_tool=0.5)
|
|
factors = ConfidenceFactors(
|
|
past_success_rate=0.9,
|
|
codebase_familiarity=0.9,
|
|
risk_assessment=0.1,
|
|
invariant_complexity=0.1,
|
|
)
|
|
op = OperationContext(operation_type="create_tool")
|
|
decision = ctrl.should_proceed_automatically(op, factors, profile)
|
|
assert decision.proceed is True, f"Expected proceed=True, got {decision.proceed}"
|
|
assert decision.confidence >= 0.5
|
|
print("threshold-proceed-ok")
|
|
|
|
|
|
def _test_threshold_escalate() -> None:
|
|
"""Escalate when confidence < threshold."""
|
|
ctrl = AutonomyController()
|
|
profile = AutomationProfile(name="test", create_tool=0.99)
|
|
factors = ConfidenceFactors(
|
|
past_success_rate=0.3,
|
|
codebase_familiarity=0.3,
|
|
risk_assessment=0.7,
|
|
invariant_complexity=0.7,
|
|
)
|
|
op = OperationContext(operation_type="create_tool")
|
|
decision = ctrl.should_proceed_automatically(op, factors, profile)
|
|
assert decision.proceed is False, f"Expected proceed=False, got {decision.proceed}"
|
|
print("threshold-escalate-ok")
|
|
|
|
|
|
def _test_history_tracking() -> None:
|
|
"""Success rate updates after recording outcomes."""
|
|
ctrl = AutonomyController()
|
|
assert abs(ctrl.get_historical_success_rate("create_tool") - 0.5) < 1e-6
|
|
|
|
for _ in range(8):
|
|
ctrl.record_outcome(
|
|
HistoricalOutcome(operation_type="create_tool", succeeded=True)
|
|
)
|
|
for _ in range(2):
|
|
ctrl.record_outcome(
|
|
HistoricalOutcome(operation_type="create_tool", succeeded=False)
|
|
)
|
|
|
|
rate = ctrl.get_historical_success_rate("create_tool")
|
|
assert abs(rate - 0.8) < 1e-6, f"Expected 0.8, got {rate}"
|
|
assert ctrl.get_history_count("create_tool") == 10
|
|
print("history-tracking-ok")
|
|
|
|
|
|
def _test_profile_manual() -> None:
|
|
"""Manual profile always escalates (with realistic confidence < 1.0)."""
|
|
ctrl = AutonomyController()
|
|
profile = BUILTIN_PROFILES["manual"]
|
|
factors = ConfidenceFactors(
|
|
past_success_rate=0.95,
|
|
codebase_familiarity=0.95,
|
|
risk_assessment=0.05,
|
|
invariant_complexity=0.05,
|
|
)
|
|
op = OperationContext(operation_type="create_tool")
|
|
decision = ctrl.should_proceed_automatically(op, factors, profile)
|
|
assert decision.proceed is False
|
|
print("profile-manual-ok")
|
|
|
|
|
|
def _test_profile_fullauto() -> None:
|
|
"""Full-auto profile always proceeds."""
|
|
ctrl = AutonomyController()
|
|
profile = BUILTIN_PROFILES["full-auto"]
|
|
factors = ConfidenceFactors(
|
|
past_success_rate=0.0,
|
|
codebase_familiarity=0.0,
|
|
risk_assessment=1.0,
|
|
invariant_complexity=1.0,
|
|
)
|
|
op = OperationContext(operation_type="create_tool")
|
|
decision = ctrl.should_proceed_automatically(op, factors, profile)
|
|
assert decision.proceed is True
|
|
print("profile-fullauto-ok")
|
|
|
|
|
|
def _test_profile_cautious() -> None:
|
|
"""Cautious profile uses intermediate thresholds."""
|
|
ctrl = AutonomyController()
|
|
profile = BUILTIN_PROFILES["cautious"]
|
|
|
|
# High confidence should proceed
|
|
high_factors = ConfidenceFactors(
|
|
past_success_rate=0.95,
|
|
codebase_familiarity=0.9,
|
|
risk_assessment=0.05,
|
|
invariant_complexity=0.05,
|
|
)
|
|
op = OperationContext(operation_type="create_tool")
|
|
high_decision = ctrl.should_proceed_automatically(
|
|
op,
|
|
high_factors,
|
|
profile,
|
|
)
|
|
assert high_decision.proceed is True
|
|
|
|
# Low confidence should escalate
|
|
low_factors = ConfidenceFactors(
|
|
past_success_rate=0.3,
|
|
codebase_familiarity=0.3,
|
|
risk_assessment=0.8,
|
|
invariant_complexity=0.8,
|
|
)
|
|
low_decision = ctrl.should_proceed_automatically(
|
|
op,
|
|
low_factors,
|
|
profile,
|
|
)
|
|
assert low_decision.proceed is False
|
|
print("profile-cautious-ok")
|
|
|
|
|
|
def _test_decision_fields() -> None:
|
|
"""Decision model includes all required fields."""
|
|
ctrl = AutonomyController()
|
|
profile = AutomationProfile(name="test", create_tool=0.5)
|
|
factors = ConfidenceFactors(
|
|
past_success_rate=0.8,
|
|
codebase_familiarity=0.7,
|
|
risk_assessment=0.2,
|
|
invariant_complexity=0.3,
|
|
)
|
|
op = OperationContext(operation_type="create_tool")
|
|
decision = ctrl.should_proceed_automatically(op, factors, profile)
|
|
|
|
assert decision.operation_type == "create_tool"
|
|
assert len(decision.factors) == 4
|
|
assert "past_success_rate" in decision.factors
|
|
assert abs(decision.threshold - 0.5) < 1e-6
|
|
assert isinstance(decision.explanation, str)
|
|
assert len(decision.explanation) > 0
|
|
print("decision-fields-ok")
|
|
|
|
|
|
def _test_zero_threshold() -> None:
|
|
"""Threshold 0.0 means always automatic, even zero confidence."""
|
|
ctrl = AutonomyController()
|
|
profile = AutomationProfile(name="test", create_tool=0.0)
|
|
factors = ConfidenceFactors(
|
|
past_success_rate=0.0,
|
|
codebase_familiarity=0.0,
|
|
risk_assessment=1.0,
|
|
invariant_complexity=1.0,
|
|
)
|
|
op = OperationContext(operation_type="create_tool")
|
|
decision = ctrl.should_proceed_automatically(op, factors, profile)
|
|
assert decision.proceed is True
|
|
assert abs(decision.confidence - 0.0) < 1e-6
|
|
print("zero-threshold-ok")
|
|
|
|
|
|
_TESTS = {
|
|
"confidence-high": _test_confidence_high,
|
|
"confidence-low": _test_confidence_low,
|
|
"threshold-proceed": _test_threshold_proceed,
|
|
"threshold-escalate": _test_threshold_escalate,
|
|
"history-tracking": _test_history_tracking,
|
|
"profile-manual": _test_profile_manual,
|
|
"profile-fullauto": _test_profile_fullauto,
|
|
"profile-cautious": _test_profile_cautious,
|
|
"decision-fields": _test_decision_fields,
|
|
"zero-threshold": _test_zero_threshold,
|
|
}
|
|
|
|
if __name__ == "__main__":
|
|
if len(sys.argv) < 2:
|
|
print(f"Usage: {sys.argv[0]} <test-name>", file=sys.stderr)
|
|
print(f"Available tests: {', '.join(sorted(_TESTS))}", file=sys.stderr)
|
|
sys.exit(1)
|
|
|
|
test_name = sys.argv[1]
|
|
if test_name not in _TESTS:
|
|
print(f"Unknown test: {test_name}", file=sys.stderr)
|
|
sys.exit(1)
|
|
|
|
_TESTS[test_name]()
|