wip: milestone v1.1 paused at phase 05 (2/3 complete)

This commit is contained in:
Variet-Worker
2026-04-07 22:42:34 +09:00
parent 7f0c688f11
commit 6014dec75b
2 changed files with 84 additions and 53 deletions

View File

@@ -1,56 +1,24 @@
{
"version": "2.0",
"timestamp": "2026-04-07T18:07:00+09:00",
"current_phase": "02-api-engine",
"phase_status": "complete",
"next_phase": "03-vscode-extension",
"completed": [
{
"phase": "01-llm-tuning",
"summary": "5개 모델 최적 추론 설정 확정",
"key_output": "config/engine_models.json",
"metrics": {
"fast_gemma4_26b": "74.65 t/s, 256K ctx, dual GPU",
"balanced_qwen_35b": "61.62 t/s, 256K ctx, dual GPU",
"deep_coder_gemma4_31b": "16.0 t/s, 192K ctx, dual GPU",
"deep_logic_qwen_27b": "16.7 t/s, 256K ctx, dual GPU",
"ultra_qwen_122b": "8.95 t/s, 256K ctx, GPU 1 only"
}
},
{
"phase": "02-api-engine",
"summary": "Variet Engine v1.0 — FastAPI 리버스 프록시 + 모델 핫스왑",
"key_output": "engine/variet_engine.py",
"features": [
"단일 포트(8000) OpenAI-compatible API",
"/engine/switch/{role} 핫스왑",
"교체 중 503+Retry-After 클라이언트 보호",
"llama-server 프로세스 생명주기 관리",
"config/engine_models.json 기반 설정"
],
"verified": true
}
"version": "1.0",
"timestamp": "2026-04-07T22:40:56+09:00",
"phase": "05",
"phase_name": "vs-code-extension-packaging",
"phase_dir": ".planning/phases/05-vscode-extension-packaging",
"plan": null,
"task": null,
"total_tasks": 0,
"status": "paused_between_phases",
"completed_tasks": [],
"remaining_tasks": [],
"blockers": [],
"human_actions_pending": [],
"decisions": [
{"decision": "OpenAI-compatible shim (CLAUDE_CODE_USE_OPENAI=1) for Variet Engine connection", "rationale": "llama-server exposes /v1 endpoints, matches OpenClaude Option 2 pattern", "phase": "03"},
{"decision": "agentRouting with single 'variet-fast' model", "rationale": "Variet Engine loads one model at a time, hot-swap via /engine/switch/{role} API", "phase": "04"},
{"decision": "Machine A IP = 192.168.10.4", "rationale": "Confirmed via Get-NetIPAddress, LAN ethernet interface", "phase": "03"},
{"decision": "--print mode sufficient for CLI validation", "rationale": "Interactive tool calls (bash, file) require terminal session, deferred to VS Code Extension phase", "phase": "04"}
],
"hardware_notes": {
"gpu0": "RTX 3060 12GB — PCIe 3.0 x4 (B550 chipset, ~4 GB/s)",
"gpu1": "RTX 3060 12GB — PCIe 4.0 x16 (CPU direct, ~32 GB/s)",
"constraint": "122B MoE는 GPU 1 단독 사용 필수 (-sm none --main-gpu 1)",
"ram": "96GB DDR4"
},
"project_structure": {
"config/engine_models.json": "5개 모델 CLI 설정 (Single Source of Truth)",
"engine/variet_engine.py": "FastAPI 프록시 + llama-server 관리자",
"start_variet_engine.bat": "원클릭 엔진 런처",
"scripts/optimal_configs.py": "실측 레퍼런스 (deprecated)",
"scripts/_archive/": "튜닝/벤치마크 이력 보관"
},
"next_steps": [
"Machine A에서 start_variet_engine.bat 상시 구동 설정 (작업 스케줄러 or 서비스)",
"Machine B에서 VS Code Extension 개발 시작 (에이전트 루프)",
"Machine B에서 Discord Bot 개발 시작 (개인 비서)"
]
"uncommitted_files": ["openclaude (submodule — node_modules/dist built locally)"],
"next_action": "/gsd-plan-phase 05 — Create VS Code Extension packaging plan, build .vsix, install on Machine B",
"context_notes": "Milestone v1.1 is 2/3 complete. Phases 03-04 done (CLI build, provider connection, agent routing, hot-swap, streaming). Phase 05 remains: package openclaude-vscode extension as .vsix with Variet Engine preset config. Variet Engine is currently running on this machine (192.168.10.4:8000, Gemma 4 26B fast role). OpenClaude CLI is built at openclaude/dist/cli.mjs."
}