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
196 lines
6.3 KiB
Python
196 lines
6.3 KiB
Python
"""ASV benchmarks for AutomationProfile validation, serialization, and guards.
|
|
|
|
Measures the performance of:
|
|
- AutomationProfile model construction (Pydantic validation)
|
|
- AutomationProfile.model_dump() serialization
|
|
- AutomationProfile.from_config() factory
|
|
- Built-in profile lookup via get_builtin_profile()
|
|
- BUILTIN_PROFILES iteration
|
|
- AutomationGuard check_guard() enforcement overhead
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
try:
|
|
from cleveragents.domain.models.core.automation_guard import (
|
|
AutomationGuard,
|
|
)
|
|
from cleveragents.domain.models.core.automation_profile import (
|
|
BUILTIN_PROFILES,
|
|
AutomationProfile,
|
|
get_builtin_profile,
|
|
)
|
|
from cleveragents.domain.models.core.safety_profile import SafetyProfile
|
|
except ModuleNotFoundError:
|
|
sys.path.insert(0, str(Path(__file__).resolve().parents[1] / "src"))
|
|
from cleveragents.domain.models.core.automation_guard import (
|
|
AutomationGuard,
|
|
)
|
|
from cleveragents.domain.models.core.automation_profile import (
|
|
BUILTIN_PROFILES,
|
|
AutomationProfile,
|
|
get_builtin_profile,
|
|
)
|
|
from cleveragents.domain.models.core.safety_profile import SafetyProfile
|
|
|
|
|
|
def _make_profile() -> AutomationProfile:
|
|
"""Create a fully-populated profile for benchmarking."""
|
|
return AutomationProfile(
|
|
name="bench/test-profile",
|
|
description="Benchmark profile",
|
|
decompose_task=0.7,
|
|
create_tool=0.5,
|
|
select_tool=1.0,
|
|
edit_code=0.6,
|
|
execute_command=0.8,
|
|
create_file=0.3,
|
|
delete_content=0.9,
|
|
access_network=0.4,
|
|
install_dependency=0.7,
|
|
modify_config=0.1,
|
|
approve_plan=0.5,
|
|
safety=SafetyProfile(
|
|
require_sandbox=True,
|
|
require_checkpoints=True,
|
|
allow_unsafe_tools=False,
|
|
),
|
|
)
|
|
|
|
|
|
class ProfileValidationSuite:
|
|
"""Benchmark AutomationProfile construction."""
|
|
|
|
def time_profile_construction(self) -> None:
|
|
"""Benchmark fully-populated profile creation."""
|
|
_make_profile()
|
|
|
|
def time_profile_minimal_construction(self) -> None:
|
|
"""Benchmark minimal profile creation."""
|
|
AutomationProfile(name="bench/minimal")
|
|
|
|
def time_profile_all_thresholds_max(self) -> None:
|
|
"""Benchmark profile with all thresholds at 1.0."""
|
|
AutomationProfile(
|
|
name="bench/max",
|
|
decompose_task=1.0,
|
|
create_tool=1.0,
|
|
select_tool=1.0,
|
|
edit_code=1.0,
|
|
execute_command=1.0,
|
|
create_file=1.0,
|
|
delete_content=1.0,
|
|
access_network=1.0,
|
|
install_dependency=1.0,
|
|
modify_config=1.0,
|
|
approve_plan=1.0,
|
|
)
|
|
|
|
|
|
class ProfileSerializationSuite:
|
|
"""Benchmark AutomationProfile serialization."""
|
|
|
|
def setup(self) -> None:
|
|
"""Create objects for serialization benchmarks."""
|
|
self.profile = _make_profile()
|
|
|
|
def time_profile_model_dump(self) -> None:
|
|
"""Benchmark model_dump() serialization."""
|
|
self.profile.model_dump()
|
|
|
|
def time_profile_model_dump_json(self) -> None:
|
|
"""Benchmark model_dump_json() JSON serialization."""
|
|
self.profile.model_dump_json()
|
|
|
|
|
|
class ProfileFromConfigSuite:
|
|
"""Benchmark AutomationProfile.from_config() factory."""
|
|
|
|
def setup(self) -> None:
|
|
"""Prepare config dicts for benchmarks."""
|
|
self.config = {
|
|
"name": "bench/from-config",
|
|
"description": "Config benchmark",
|
|
"decompose_task": 0.7,
|
|
"create_tool": 0.5,
|
|
"select_tool": 1.0,
|
|
}
|
|
|
|
def time_profile_from_config(self) -> None:
|
|
"""Benchmark from_config()."""
|
|
AutomationProfile.from_config(self.config)
|
|
|
|
|
|
class BuiltinProfileSuite:
|
|
"""Benchmark built-in profile operations."""
|
|
|
|
def time_get_builtin_profile(self) -> None:
|
|
"""Benchmark get_builtin_profile() lookup."""
|
|
get_builtin_profile("cautious")
|
|
|
|
def time_iterate_all_builtins(self) -> None:
|
|
"""Benchmark iterating all built-in profiles."""
|
|
for name in BUILTIN_PROFILES:
|
|
_ = BUILTIN_PROFILES[name]
|
|
|
|
|
|
class GuardCheckSuite:
|
|
"""Benchmark AutomationGuard check_guard() operations."""
|
|
|
|
def setup(self) -> None:
|
|
"""Create profiles with various guard configurations."""
|
|
self.no_guard_profile = AutomationProfile(name="bench/no-guard")
|
|
self.guarded_profile = AutomationProfile(
|
|
name="bench/guarded",
|
|
guards=AutomationGuard(
|
|
max_tool_calls_per_step=10,
|
|
max_total_cost=100.0,
|
|
tool_denylist=["dangerous_tool"],
|
|
tool_allowlist=["safe_tool", "read_file", "list_dir"],
|
|
require_approval_for_writes=True,
|
|
require_approval_for_apply=True,
|
|
),
|
|
)
|
|
self.minimal_guard = AutomationProfile(
|
|
name="bench/minimal-guard",
|
|
guards=AutomationGuard(max_tool_calls_per_step=50),
|
|
)
|
|
|
|
def time_check_guard_no_guards(self) -> None:
|
|
"""Benchmark check_guard with no guards configured."""
|
|
self.no_guard_profile.check_guard("any_tool")
|
|
|
|
def time_check_guard_allowed(self) -> None:
|
|
"""Benchmark check_guard when tool is allowed."""
|
|
self.guarded_profile.check_guard("safe_tool", calls_so_far=5)
|
|
|
|
def time_check_guard_denied(self) -> None:
|
|
"""Benchmark check_guard when tool is on denylist."""
|
|
self.guarded_profile.check_guard("dangerous_tool")
|
|
|
|
def time_check_guard_write(self) -> None:
|
|
"""Benchmark check_guard with write flag."""
|
|
self.guarded_profile.check_guard("safe_tool", is_write=True)
|
|
|
|
def time_check_guard_cost(self) -> None:
|
|
"""Benchmark check_guard with cost check."""
|
|
self.guarded_profile.check_guard(
|
|
"safe_tool",
|
|
cost_so_far=50.0,
|
|
)
|
|
|
|
def time_check_guard_minimal(self) -> None:
|
|
"""Benchmark check_guard with minimal guard config."""
|
|
self.minimal_guard.check_guard("tool", calls_so_far=10)
|
|
|
|
def time_guard_construction(self) -> None:
|
|
"""Benchmark AutomationGuard model construction."""
|
|
AutomationGuard(
|
|
max_tool_calls_per_step=10,
|
|
max_total_cost=100.0,
|
|
tool_denylist=["tool_a", "tool_b"],
|
|
)
|