Variet/variet_llm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: start milestone v1.1 OpenClaude CLI Integration

Browse Source
This commit is contained in:
Variet-Worker
2026-04-07 20:39:36 +09:00
parent c111b3a9b0
commit 7e39c002b6
2 changed files with 22 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
.planning/PROJECT.md
View File

@@ -18,6 +18,7 @@ Single developer working on complex coding tasks alongside daily administrative
| 5-Tier Model Strategy | Need balanced speeds depending on the complexity of the task requested. | Fast: Gemma4 26B (~75t/s)<br/>Balanced: Qwen 35B (~62t/s)<br/>Deep-Coder: Gemma4 31B (~16t/s)<br/>Deep-Logic: Qwen 27B (~17t/s)<br/>Ultra: Qwen 122B (~9t/s) | | 5-Tier Model Strategy | Need balanced speeds depending on the complexity of the task requested. | Fast: Gemma4 26B (~75t/s)<br/>Balanced: Qwen 35B (~62t/s)<br/>Deep-Coder: Gemma4 31B (~16t/s)<br/>Deep-Logic: Qwen 27B (~17t/s)<br/>Ultra: Qwen 122B (~9t/s) |
| GPU 0 PCIe x4 제약 | GPU 0이 PCIe 3.0 x4 슬롯에 물려 대역폭이 1/8. MoE 모델(122B)은 GPU 1 단독 사용 필수. | Dense 모델은 듀얼 GPU, MoE Ultra는 GPU 1 전용 | | GPU 0 PCIe x4 제약 | GPU 0이 PCIe 3.0 x4 슬롯에 물려 대역폭이 1/8. MoE 모델(122B)은 GPU 1 단독 사용 필수. | Dense 모델은 듀얼 GPU, MoE Ultra는 GPU 1 전용 |
| Variet Engine (FastAPI 프록시) | 단일 포트(8000)에서 모든 API 중계 + 핫스왑. 개별 .bat 파일 난립 해소. | `engine/variet_engine.py` + `config/engine_models.json` | | Variet Engine (FastAPI 프록시) | 단일 포트(8000)에서 모든 API 중계 + 핫스왑. 개별 .bat 파일 난립 해소. | `engine/variet_engine.py` + `config/engine_models.json` |
| CLI-First 검증 전략 | VS Code Extension 개발 전 OpenClaude CLI로 먼저 에이전트 루프를 검증. 빠른 피드백 루프 확보. | `openclaude/` 서브모듈 (v0.1.8) → Variet Engine 연결 |
## Requirements ## Requirements
@@ -28,6 +29,9 @@ Single developer working on complex coding tasks alongside daily administrative
### Active ### Active
- [ ] Connect OpenClaude CLI to Variet Engine for terminal-based coding agent. *(Phase 03)*
- [ ] Configure 5-Tier model routing (agentRouting) in OpenClaude. *(Phase 03)*
- [ ] Validate end-to-end agent loop: prompt → tool calls → code changes. *(Phase 03)*
- [ ] Develop a VS Code Extension (TypeScript) on Machine B for coding agent loop. - [ ] Develop a VS Code Extension (TypeScript) on Machine B for coding agent loop.
- [ ] Develop a Discord Bot (discord.py) on Machine B for personal assistant tools. - [ ] Develop a Discord Bot (discord.py) on Machine B for personal assistant tools.
- [ ] Implement MCP tools (SearXNG, Google Calendar, Gmail) securely on Machine B. - [ ] Implement MCP tools (SearXNG, Google Calendar, Gmail) securely on Machine B.
@@ -37,8 +41,18 @@ Single developer working on complex coding tasks alongside daily administrative
- [ ] Running inference directly on Machine B (It lacks VRAM/GPU resources in this architecture). - [ ] Running inference directly on Machine B (It lacks VRAM/GPU resources in this architecture).
- [ ] Exposing Machine A to the public internet (LAN traffic only). - [ ] Exposing Machine A to the public internet (LAN traffic only).
## Current Milestone: v1.1 OpenClaude CLI Integration
**Goal:** OpenClaude CLI를 Variet Engine에 연결하여 Machine B에서 터미널 기반 코딩 에이전트를 가동하고 검증한다.
**Target features:**
- OpenClaude → Variet Engine (Machine A:8000) 프로바이더 연결
- 5-Tier 모델 라우팅 (agentRouting) 설정
- CLI 빌드 및 동작 검증
- Variet Engine 핫스왑 연동 테스트
--- ---
*Last updated: 2026-04-07 after Phase 02 completion* *Last updated: 2026-04-07 — Milestone v1.1 started*
## Evolution ## Evolution

18
.planning/STATE.md
View File

@@ -4,9 +4,10 @@
A high-performance, locally-hosted AI assistant system built on two RTX 3060 12GB GPUs. It uses a "2+0" architecture where Machine A acts as a dedicated inference server running large language models, while Machine B handles the user interface (VS Code, Discord) and tool execution. A high-performance, locally-hosted AI assistant system built on two RTX 3060 12GB GPUs. It uses a "2+0" architecture where Machine A acts as a dedicated inference server running large language models, while Machine B handles the user interface (VS Code, Discord) and tool execution.
## Current Position ## Current Position
Phase: 02-api-engine (Complete) -> Ready for Phase 3 Phase: Not started (defining requirements)
Plan: None Plan: —
Status: Transitioning to Phase 3 Status: Defining requirements
Last activity: 2026-04-07 — Milestone v1.1 started
## Progress ## Progress
[████████████████████] 100% (Phase 01: LLM Tuning) [████████████████████] 100% (Phase 01: LLM Tuning)
@@ -22,6 +23,7 @@ Status: Transitioning to Phase 3
- GPU 0 PCIe x4 제약 → 122B MoE는 GPU 1 단독 사용. - GPU 0 PCIe x4 제약 → 122B MoE는 GPU 1 단독 사용.
- Variet Engine: 단일 포트(8000) FastAPI 리버스 프록시. - Variet Engine: 단일 포트(8000) FastAPI 리버스 프록시.
- config/engine_models.json → 모든 설정의 Single Source of Truth. - config/engine_models.json → 모든 설정의 Single Source of Truth.
- CLI-First 검증 전략: VS Code Extension 전 OpenClaude CLI로 에이전트 루프 먼저 검증.
## Pending Todos ## Pending Todos
0 pending. 0 pending.
@@ -29,12 +31,6 @@ Status: Transitioning to Phase 3
## Blockers/Concerns ## Blockers/Concerns
None. None.
## Next Phases (Suggested)
- Phase 03: VS Code Extension (에이전트 루프, 도구 통합)
- Phase 04: Discord Bot (개인 비서, 슬래시 명령어)
- Phase 05: MCP Tools (SearXNG, Calendar, Gmail)
## Session Continuity ## Session Continuity
Last session: 2026-04-07T18:07:00+09:00 Last session: 2026-04-07T20:38:00+09:00
Stopped at: Phase 02 complete, GSD sync in progress Milestone: v1.1 OpenClaude CLI Integration
Resume file: .planning/HANDOFF.json