Lap Tran
7336db282d
CI / build (push) Has been cancelled
Self-improvement loop:
- Created via --create-loop --from-template self-improvement
- Scheduled via launchd (3600s interval)
- State: running
model-divergence-enforcement task:
- Research approved, decomposed into 3 sequential subtasks:
1. mde-manifest-detection (models.json + detect_models.py)
2. mde-interactive-enforcement (conflict matrix + --model args + audit)
3. mde-loop-enforcement (loop.json roles + {model} substitution + check-gate)
- Parent at decomposition:approved (stays active until subtasks complete)
- Each subtask has BRIEF.md with scope, deliverables, acceptance criteria
1.4 KiB
1.4 KiB
BRIEF — mde-loop-enforcement
Parent: model-divergence-enforcement
Subtask: 3 of 3 (depends on mde-interactive-enforcement)
Spec ref: tasks/model-divergence-enforcement/SPEC.md §Subtask 3
Design ref: design/framework/technical.md §§10, §13
Objective
Add loop-level model-divergence enforcement: loop.json per-role model field,
{model} substitution in _invoke_harness, and --check-gate model-divergence
brake gate.
Deliverables
scripts/loop-runner.py:_invoke_harness(line 366-404):{model}placeholder substitution fromloop.jsonrole config
scripts/status.py:--check-gate: model-divergence brake gate (loop-verify ≠ loop-implement in multi-LLM mode)cmd_create_loop/cmd_install_schedule: validateloop.jsonper-rolemodelfields
templates/loops/: update loop templates withrolesschema exampledesign/loops/technical.md: document{model}substitutiontests/test_model_divergence.py: loop model binding,{model}substitution, check-gate halt
Acceptance
loop.jsonwithroles.implementer.model→_invoke_harnesssubstitutes{model}in harness commandloop.jsonwithout per-rolemodel→ defaults tomodels.jsondefaultmodel--check-gatein multi-LLM mode halts if loop-verify model = loop-implement model--check-gatein single-LLM mode does NOT halt (advisory only)pytest tests/ -qgreen