forked from cleveragents/cleveragents-core
CoreRasurae
66b9a4279f
Add SafetyProfile domain model with configurable safety constraints (checkpoint, human approval, cost limits, retry limits, skill categories, sandbox requirement). Integrate into Action model with from_config/as_cli_dict support, and persist via LifecycleActionModel safety_profile_json column. Include resolve_safety_profile() stub that raises NotImplementedError for local mode, signalling that real enforcement is deferred. Add comprehensive test coverage: - 20 BDD scenarios in features/safety_profile.feature - 6 Robot Framework smoke tests - 5 ASV benchmark suites (11 timing functions) Add docs/reference/safety_profile.md reference documentation. ISSUES CLOSED: #332
33 lines
705 B
YAML
33 lines
705 B
YAML
# Built-in profile: ci
|
|
# Designed for CI pipelines.
|
|
# All thresholds at 0.0 — fully automatic in a sandboxed environment.
|
|
|
|
name: ci
|
|
description: Designed for CI pipelines
|
|
schema_version: "1.0"
|
|
|
|
# Phase-transition thresholds
|
|
auto_strategize: 0.0
|
|
auto_execute: 0.0
|
|
auto_apply: 0.0
|
|
|
|
# Decision-autonomy thresholds
|
|
auto_decisions_strategize: 0.0
|
|
auto_decisions_execute: 0.0
|
|
|
|
# Self-repair thresholds
|
|
auto_validation_fix: 0.0
|
|
auto_strategy_revision: 0.0
|
|
auto_reversion_from_apply: 0.0
|
|
|
|
# Child plan and retry thresholds
|
|
auto_child_plans: 0.0
|
|
auto_retry_transient: 0.0
|
|
auto_checkpoint_restore: 0.0
|
|
|
|
# Safety requirements
|
|
safety:
|
|
require_sandbox: true
|
|
require_checkpoints: true
|
|
allow_unsafe_tools: false
|