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
175 lines
4.9 KiB
YAML
175 lines
4.9 KiB
YAML
# Automation Profile YAML Schema
|
|
# Defines the expected structure for automation profile configuration files.
|
|
# See docs/specification.md Section "Automation Profiles" for full details.
|
|
|
|
type: object
|
|
required:
|
|
- name
|
|
additionalProperties: false
|
|
properties:
|
|
name:
|
|
type: string
|
|
minLength: 1
|
|
pattern: "^[a-zA-Z0-9_-]+(/[a-zA-Z0-9_-]+)?$"
|
|
description: >
|
|
Profile name: bare built-in name (e.g. 'manual')
|
|
or namespaced 'namespace/name' (e.g. 'acme/strict')
|
|
description:
|
|
type: string
|
|
description: "Human-readable description of the profile"
|
|
schema_version:
|
|
type: string
|
|
default: "1.0"
|
|
description: "Schema version for forward compatibility"
|
|
|
|
# Task-type confidence thresholds (0.0 = auto, 1.0 = human)
|
|
decompose_task:
|
|
type: number
|
|
minimum: 0.0
|
|
maximum: 1.0
|
|
default: 0.0
|
|
description: "Threshold for automatic task decomposition"
|
|
create_tool:
|
|
type: number
|
|
minimum: 0.0
|
|
maximum: 1.0
|
|
default: 0.0
|
|
description: "Threshold for automatic tool creation"
|
|
select_tool:
|
|
type: number
|
|
minimum: 0.0
|
|
maximum: 1.0
|
|
default: 0.0
|
|
description: "Threshold for automatic tool selection"
|
|
|
|
edit_code:
|
|
type: number
|
|
minimum: 0.0
|
|
maximum: 1.0
|
|
default: 0.0
|
|
description: "Threshold for automatic code editing"
|
|
execute_command:
|
|
type: number
|
|
minimum: 0.0
|
|
maximum: 1.0
|
|
default: 0.0
|
|
description: "Threshold for automatic command execution"
|
|
|
|
create_file:
|
|
type: number
|
|
minimum: 0.0
|
|
maximum: 1.0
|
|
default: 0.0
|
|
description: "Threshold for automatic file creation"
|
|
delete_content:
|
|
type: number
|
|
minimum: 0.0
|
|
maximum: 1.0
|
|
default: 0.0
|
|
description: "Threshold for automatic content deletion"
|
|
access_network:
|
|
type: number
|
|
minimum: 0.0
|
|
maximum: 1.0
|
|
default: 0.0
|
|
description: "Threshold for automatic network access"
|
|
|
|
install_dependency:
|
|
type: number
|
|
minimum: 0.0
|
|
maximum: 1.0
|
|
default: 0.0
|
|
description: "Threshold for automatic dependency installation"
|
|
modify_config:
|
|
type: number
|
|
minimum: 0.0
|
|
maximum: 1.0
|
|
default: 0.0
|
|
description: "Threshold for automatic configuration modification"
|
|
approve_plan:
|
|
type: number
|
|
minimum: 0.0
|
|
maximum: 1.0
|
|
default: 0.0
|
|
description: "Threshold for automatic plan approval"
|
|
|
|
# Optional automation guards (runtime enforcement hooks)
|
|
guards:
|
|
type: ["object", "null"]
|
|
description: "Optional AutomationGuard sub-model with per-invocation runtime constraints"
|
|
properties:
|
|
max_tool_calls_per_step:
|
|
type: ["integer", "null"]
|
|
minimum: 0
|
|
default: null
|
|
description: "Maximum tool invocations per step before requiring approval"
|
|
max_total_cost:
|
|
type: ["number", "null"]
|
|
minimum: 0.0
|
|
default: null
|
|
description: "Maximum cumulative invocation cost before requiring approval"
|
|
tool_allowlist:
|
|
type: ["array", "null"]
|
|
items:
|
|
type: string
|
|
default: null
|
|
description: "Only these tools may proceed automatically (null = all tools)"
|
|
tool_denylist:
|
|
type: ["array", "null"]
|
|
items:
|
|
type: string
|
|
default: null
|
|
description: "These tools always require approval (null = no denied tools)"
|
|
require_approval_for_writes:
|
|
type: boolean
|
|
default: false
|
|
description: "Require approval for write operations"
|
|
require_approval_for_apply:
|
|
type: boolean
|
|
default: false
|
|
description: "Require approval before apply phase"
|
|
|
|
# Safety profile (composed sub-model)
|
|
safety:
|
|
type: object
|
|
description: "Composed SafetyProfile sub-model with hard safety constraints"
|
|
properties:
|
|
require_sandbox:
|
|
type: boolean
|
|
default: true
|
|
description: "Whether a sandbox is required for execution"
|
|
require_checkpoints:
|
|
type: boolean
|
|
default: true
|
|
description: "Whether checkpoints are required"
|
|
allow_unsafe_tools:
|
|
type: boolean
|
|
default: false
|
|
description: "Whether unsafe tools may be used"
|
|
require_human_approval:
|
|
type: boolean
|
|
default: false
|
|
description: "Whether human approval is required before each action step"
|
|
allowed_skill_categories:
|
|
type: array
|
|
items:
|
|
type: string
|
|
default: []
|
|
description: "Skill categories permitted for execution (empty = all allowed)"
|
|
max_cost_per_plan:
|
|
type: ["number", "null"]
|
|
minimum: 0.0
|
|
default: null
|
|
description: "Maximum cost in USD per plan execution (null = no limit)"
|
|
max_total_cost:
|
|
type: ["number", "null"]
|
|
minimum: 0.0
|
|
default: null
|
|
description: "Maximum total cost in USD across all plans (null = no limit)"
|
|
max_retries_per_step:
|
|
type: integer
|
|
minimum: 0
|
|
maximum: 100
|
|
default: 3
|
|
description: "Maximum retry attempts per action step"
|