[codex] add loop engineering runtime

[dreambloomdesign-code]

Release DESIGNOSFORGE v2.1.0

Summary

• Add Loop Engineering as a system-runtime layer for long-running agent loops.
• Add LoopEngineeringBlueprintBuilder and LoopEngineeringOS.
• Add kernel loop-engineering CLI export.
• Document the six-question loop contract: scheduler, isolation, skill context, connectors, validation, and memory.
• Keep PromptPacketV2 and LoopPromptPack independent and backward compatible.
• Strengthen GitHub/CI/worktree workflow planning and release validation.

Validation

• py -m compileall app tests tools
• py -m app.cli capabilities
• py -m app.cli kernel loop-engineering "Loop Engineering 调度 issue CI，worktree 并行隔离，validator 验收，写入长期记忆"
• py -m app.cli kernel loop-prompt "create a design prompt with three loop iterations and self critique"
• py -m pytest -q
• py tools\validate_source_skill.py
• Skill quick_validate passed

Compatibility

This is additive. Existing PromptPacketV2, LoopPromptPack, LoRA memory, EnvArt CADMCP, photography workflows, and GitHub management remain intact.

Rollback

Revert the release commit or restore the previous tag.

[dreambloomdesign-code]

Local validation for v2.1 Loop Engineering upgrade:

• PASS: py -m compileall app tests tools
• PASS: source skill validator: tools/validate_source_skill.py
• PASS: installed Codex skill quick_validate
• PASS: CLI smoke: capabilities includes DESIGNOSFORGE v2.1.0, LoopEngineeringOS, Capability Call Table
• PASS: CLI smoke: kernel loop-engineering emits LoopEngineeringBlueprint, event_trigger, git_worktree_per_agent, persistent_memory
• PASS: lightweight local test runner executed 17 test functions
• NOTE: direct pytest invocation was not available locally because pytest is not installed in the available Python runtimes; tests were executed by direct function calls instead.