Implemented the first version of the operator resolution guidance framework. Added new foundation classes (ResolutionCase, ResolutionAction) and a ReviewPackOutputResolutionAdapter. Updated the Customer Review Workspace and Environment Review Resource to use the new adapter. Added extensive test coverage for the framework and UI integrations. Co-authored-by: Ahmed Darrazi <ahmed.darrazi@live.de> Reviewed-on: #421
1.7 KiB
1.7 KiB
Future AI / Human-in-the-Loop Extension
Status: Draft for Spec 350
Scope: Documentation only
Current Rule
Spec 350 does not implement AI.
No runtime AI call, no AI suggestion rendering, and no AI-driven execution path are part of v1.
Why This Document Exists
The shared case/action contract is a plausible future attachment point for AI-assisted guidance. Documenting that boundary now avoids later feature-local AI drift.
Reserved Extension Shape
If a later spec enables AI suggestions, the ResolutionCase envelope may gain a strictly optional field like:
[
'ai_suggestion' => [
'enabled' => false,
'provider' => null,
'model' => null,
'confidence' => null,
'summary' => null,
'requires_human_approval' => true,
'policy_gate' => null,
'budget_gate' => null,
'context_refs' => [],
],
]
That field must stay absent or disabled in Spec 350 runtime work.
Mandatory Future Gates
Any future AI-enabled follow-up must require:
- AI policy gate
- AI context boundary
- AI budget/cost gate
- audit trail
- human approval gate
- capability gate
- existing domain action or
OperationRunexecution path
Forbidden Future Shortcuts
- direct AI execution without human approval
- direct AI writes around existing policy/capability checks
- storing AI-generated resolution truth as canonical truth without a separate spec
- bypassing existing audit requirements
Current Implementation Guidance
Spec 350 runtime work should leave clear seams for later extension but should not:
- add AI fields to rendered UI
- add AI fields to persisted rows
- add AI-specific copy keys
- add AI-specific jobs or service calls