CoreRasurae
66b9a4279f
CI / benchmark-publish (pull_request) Has been skipped
CI / lint (pull_request) Successful in 15s
CI / build (pull_request) Successful in 15s
CI / quality (pull_request) Successful in 17s
CI / security (pull_request) Successful in 32s
CI / typecheck (pull_request) Successful in 35s
CI / unit_tests (pull_request) Successful in 1m55s
CI / docker (pull_request) Successful in 39s
CI / integration_tests (pull_request) Successful in 2m50s
CI / coverage (pull_request) Successful in 4m13s
CI / benchmark-regression (pull_request) Successful in 23m10s
CI / lint (push) Successful in 12s
CI / quality (push) Successful in 15s
CI / build (push) Successful in 15s
CI / security (push) Successful in 29s
CI / typecheck (push) Successful in 32s
CI / benchmark-regression (push) Has been skipped
CI / unit_tests (push) Successful in 3m10s
CI / docker (push) Successful in 38s
CI / integration_tests (push) Successful in 4m1s
CI / coverage (push) Successful in 3m58s
CI / benchmark-publish (push) Successful in 13m21s
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
745 B
YAML
33 lines
745 B
YAML
# Built-in profile: supervised
|
|
# Human reviews strategy and execution phases.
|
|
# Strategy is automatic; execution and apply require human review.
|
|
|
|
name: supervised
|
|
description: Human reviews strategy and execution
|
|
schema_version: "1.0"
|
|
|
|
# Phase-transition thresholds
|
|
auto_strategize: 0.0
|
|
auto_execute: 1.0
|
|
auto_apply: 1.0
|
|
|
|
# Decision-autonomy thresholds
|
|
auto_decisions_strategize: 0.0
|
|
auto_decisions_execute: 1.0
|
|
|
|
# Self-repair thresholds
|
|
auto_validation_fix: 1.0
|
|
auto_strategy_revision: 1.0
|
|
auto_reversion_from_apply: 1.0
|
|
|
|
# Child plan and retry thresholds
|
|
auto_child_plans: 1.0
|
|
auto_retry_transient: 0.0
|
|
auto_checkpoint_restore: 1.0
|
|
|
|
# Safety requirements
|
|
safety:
|
|
require_sandbox: true
|
|
require_checkpoints: true
|
|
allow_unsafe_tools: false
|