daviestechlabs/homelab-design
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

ADR-0062: BlenderMCP 3D avatar workflow with Kasm, gravenhollow NFS, and Cloudflare R2
Some checks failed
Update README with ADR Index / update-readme (push) Has been cancelled
Details

Browse Source
This commit is contained in:
Billy Davies
2026-02-21 16:13:36 -05:00
parent defbd5b2f9
commit 9fe12e0cff
1 changed files with 444 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

444
decisions/0062-blender-mcp-3d-avatar-workflow.md Normal file
View File

@@ -0,0 +1,444 @@
# BlenderMCP for 3D Avatar Creation via Kasm Workstation
* Status: proposed
* Date: 2026-02-21
* Deciders: Billy
* Technical Story: Enable AI-assisted 3D avatar creation for companions-frontend using BlenderMCP in a Kasm Blender workstation with VS Code, storing assets in S3, serving locally from gravenhollow NFS and remotely via Cloudflare R2 CDN
## Context and Problem Statement
The companions-frontend serves VRM avatar models for its Three.js-based 3D character rendering (see [ADR-0046](0046-companions-frontend-architecture.md)). Today the avatar library is limited to three models (`Seed-san.vrm`, `Aka.vrm`, `Midori.vrm`) — only one of which actually ships in the repo — and every model must be sourced or hand-sculpted externally.
Creating custom VRM avatars is a manual, time-intensive process: open Blender, sculpt/rig a character, export to VRM, iterate. There is no integration between the AI coding workflow (VS Code / Copilot) and Blender, so context switching between the editor and the 3D tool is constant.
How do we streamline custom 3D avatar creation for companions-frontend with AI assistance, while keeping assets durable and accessible across workstations?
## Decision Drivers
* The existing avatar pipeline is manual and disconnected from the development workflow
* BlenderMCP (v1.5.5, 17k+ GitHub stars) bridges AI assistants to Blender via the Model Context Protocol — enabling prompt-driven 3D modelling, material control, scene manipulation, and code execution inside Blender
* Kasm Workspaces already run in the cluster (`productivity` namespace) and support Docker-in-Docker with volume plugins for persistent storage
* VS Code supports MCP servers natively (GitHub Copilot agent mode), meaning the same editor used for code can drive Blender scene creation
* Custom volume mounts in Kasm map `/s3` to S3-compatible storage via the rclone Docker volume plugin — providing durable, off-node persistence
* Quobyte S3-compatible endpoint with the `kasm` bucket is the existing Kasm storage backend
* VRM models must ultimately land in the companions-frontend `/assets/models/` path at build time or be served from an external URL
* Final production models and animations should live on gravenhollow (all-SSD TrueNAS, dual 10GbE) for fast local serving via NFS
* Remote users accessing companions-chat through Cloudflare Tunnel need a CDN-backed path for multi-MB VRM downloads
* Models are write-once/read-many — ideal for aggressive caching
## Considered Options
1. **BlenderMCP in Kasm Blender workstation + VS Code MCP client, assets in Quobyte S3 (`kasm` bucket)**
2. **Local Blender + BlenderMCP on a developer laptop**
3. **Hyper3D / Rodin cloud generation only (no Blender)**
4. **Manual Blender workflow (status quo)**
## Decision Outcome
Chosen option: **Option 1 — BlenderMCP in Kasm Blender workstation + VS Code MCP client, assets in Quobyte S3**, because it integrates AI-assisted modelling directly into the existing Kasm + VS Code workflow, stores assets durably in S3, and requires no additional infrastructure beyond what is already deployed.
### Positive Consequences
* AI-assisted 3D modelling — prompt-driven creation, material application, and scene manipulation inside Blender via MCP
* Zero context switching — VS Code agent mode drives Blender commands through the same editor used for code
* Persistent storage — VRM exports written to `/s3` survive session teardown and are available from any Kasm session or CI pipeline
* Existing infrastructure — Kasm agent, DinD, rclone volume plugin, Quobyte S3, gravenhollow NFS, and Cloudflare are all already deployed
* No image rebuild for new models — VRM files live on gravenhollow NFS, mounted read-only into the pod; add a model and update the allowlist
* LAN performance — all-SSD NFS with dual 10GbE delivers VRM files in <100ms
* Remote performance — Cloudflare R2 CDN with zero egress fees and 300+ global PoPs for remote users via Cloudflare Tunnel
* Poly Haven / Hyper3D integration — BlenderMCP supports downloading Poly Haven assets and generating models via Hyper3D Rodin, expanding the asset library
* VRM ecosystem — Blender VRM add-on exports directly to VRM 0.x/1.0 format consumed by `@pixiv/three-vrm` in companions-frontend
* Reproducible — Kasm workspace images are versioned; Blender + add-ons are pre-baked
### Negative Consequences
* BlenderMCP `execute_blender_code` tool runs arbitrary Python in Blender — must trust AI-generated code or review before execution
* Socket-based communication (TCP 9876) between the MCP server and Blender add-on adds a failure mode
* VRM export quality depends on correct rigging/weight painting — AI can scaffold but manual touch-up may still be needed
* Kasm Blender image must be configured with both the BlenderMCP add-on and the VRM add-on pre-installed
* Telemetry is on by default in BlenderMCP — must disable via `DISABLE_TELEMETRY=true` for privacy
* Cloudflare R2 sync adds a CronJob and requires a Cloudflare R2 API token in Vault
* Two-hop promotion path (Quobyte S3 → gravenhollow NFS → Cloudflare R2) adds operational steps
## Architecture
```
┌─────────────────────────────────────────────────────────────────────────┐
│ Developer Workstation │
│ │
│ ┌──────────────────────────────────┐ │
│ │ VS Code (local) │ │
│ │ │ │
│ │ GitHub Copilot (agent mode) │ │
│ │ │ │ │
│ │ ▼ │ │
│ │ BlenderMCP Server (MCP) │ │
│ │ (uvx blender-mcp) │ │
│ │ │ │ │
│ └─────────┼────────────────────────┘ │
│ │ TCP :9876 (JSON over socket) │
└────────────┼────────────────────────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────────────────────────────────┐
│ Kasm Blender Workstation (browser session) │
│ kasm.daviestechlabs.io │
│ │
│ ┌──────────────────────────────────────────────────────┐ │
│ │ Blender 4.x │ │
│ │ │ │
│ │ Add-ons: │ │
│ │ • BlenderMCP (addon.py) — socket server :9876 │ │
│ │ • VRM Add-on for Blender — import/export VRM │ │
│ │ │ │
│ │ ┌────────────────────────────────────────────────┐ │ │
│ │ │ /s3/blender-avatars/ │ │ │
│ │ │ ├── projects/ (.blend source files) │ │ │
│ │ │ ├── exports/ (.vrm exported models) │ │ │
│ │ │ └── textures/ (shared texture lib) │ │ │
│ │ └────────────────────────────────────────────────┘ │ │
│ └──────────────────────────────────────────────────────┘ │
│ │ │
│ rclone volume │
│ plugin (S3) │
└──────────────────────────┼──────────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────────────────────────────────┐
│ Quobyte S3 Endpoint │
│ Bucket: kasm │
│ │
│ kasm/blender-avatars/projects/Companion-A.blend │
│ kasm/blender-avatars/exports/Companion-A.vrm │
│ kasm/blender-avatars/textures/skin-tone-01.png │
└──────────────────────────┬──────────────────────────────────────────────┘
│
rclone sync (promotion)
│
▼
┌─────────────────────────────────────────────────────────────────────────┐
│ gravenhollow.lab.daviestechlabs.io │
│ (TrueNAS Scale · All-SSD · Dual 10GbE · 12.2 TB) │
│ │
│ NFS: /mnt/gravenhollow/kubernetes/avatar-models/ │
│ ├── Seed-san.vrm (default model) │
│ ├── Aka.vrm (Legend tier) │
│ ├── Midori.vrm (Legend tier) │
│ ├── Companion-A.vrm (custom, promoted from Kasm S3) │
│ └── animations/ (shared animation clips) │
│ │
│ S3 (RustFS): avatar-models bucket │
│ (mirror of NFS dir for Cloudflare R2 sync) │
└──────────┬─────────────────────────────────┬────────────────────────────┘
│ │
NFS mount (nfs-fast) rclone sync (cron)
│ │
▼ ▼
┌──────────────────────────┐ ┌──────────────────────────────────────────┐
│ companions-frontend │ │ Cloudflare R2 │
│ (Kubernetes pod) │ │ Bucket: avatar-models │
│ │ │ │
│ /models/ volume mount │ │ Custom domain: │
│ (nfs-fast PVC, RO) │ │ assets.daviestechlabs.io/models/ │
│ │ │ │
│ Go FileServer: │ │ Cache-Control: public, max-age=31536000 │
│ /assets/models/ → │ │ (immutable, versioned filenames) │
│ serves from PVC │ │ │
│ │ │ Free egress (no bandwidth charges) │
└──────────┬───────────────┘ └──────────────────────┬───────────────────┘
│ │
LAN clients Remote clients
companions-chat.lab... companions-chat via
(envoy-internal, direct) Cloudflare Tunnel
│ │
└──────────────────┬───────────────────────┘
▼
┌─────────────────────────────────────────────────────────────────────────┐
│ Browser (Three.js) │
│ AvatarManager.loadModel('/assets/models/Companion-A.vrm') │
│ │
│ LAN: fetch from companions-frontend pod (NFS-backed, ~10GbE) │
│ Remote: fetch from Cloudflare R2 CDN (cache-hit, global PoPs) │
└─────────────────────────────────────────────────────────────────────────┘
```
## Workflow
### 1. Kasm Workspace Setup
The Kasm Blender workspace image is configured with:
| Component | Version | Purpose |
|-----------|---------|---------|
| Blender | 4.x | 3D modelling and sculpting |
| BlenderMCP add-on (`addon.py`) | 1.5.5 | Socket server for MCP commands |
| VRM Add-on for Blender | latest | Import/export VRM format |
| Python | 3.10+ | Blender scripting runtime |
The Kasm storage mapping mounts `/s3` via the rclone Docker volume plugin to the Quobyte S3 endpoint (`kasm` bucket). The sub-path `blender-avatars/` is used for all 3D asset work.
### 2. VS Code MCP Configuration
Add BlenderMCP as an MCP server in VS Code (`.vscode/mcp.json` or user settings):
```json
{
"servers": {
"blender": {
"command": "uvx",
"args": ["blender-mcp"],
"env": {
"BLENDER_HOST": "localhost",
"BLENDER_PORT": "9876",
"DISABLE_TELEMETRY": "true"
}
}
}
}
```
When the Kasm session is accessed remotely, set `BLENDER_HOST` to the Kasm workstation's reachable address.
### 3. Avatar Creation Workflow
1. **Launch** the Kasm Blender workspace via `kasm.daviestechlabs.io`
2. **Enable** the BlenderMCP add-on in Blender → 3D View sidebar → "BlenderMCP" tab → "Connect to Claude"
3. **Open VS Code** with Copilot agent mode and the BlenderMCP MCP server running
4. **Prompt** the AI to create or modify avatars:
- _"Create a humanoid character with anime-style proportions, blue hair, and a fantasy outfit"_
- _"Apply a metallic gold material to the armor pieces"_
- _"Set up the lighting for a character showcase render"_
- _"Rig this character for VRM export with standard humanoid bones"_
5. **Export** the finished model to VRM via the VRM add-on (or via BlenderMCP `execute_blender_code` calling the VRM export operator)
6. **Save** the `.vrm` to `/s3/blender-avatars/exports/` and the `.blend` source to `/s3/blender-avatars/projects/`
7. **Import** the VRM into companions-frontend — copy to `assets/models/`, update the allowlists in `internal/database/database.go` and `static/js/avatar.js`
### 4. Asset Pipeline (Kasm S3 → gravenhollow → production)
| Stage | Action |
|-------|--------|
| **Create** | AI-assisted modelling + VRM export in Kasm Blender → `/s3/blender-avatars/exports/*.vrm` |
| **Store** | rclone syncs `/s3` to Quobyte S3 `kasm` bucket automatically |
| **Promote** | `rclone copy quobyte:kasm/blender-avatars/exports/Model.vrm gravenhollow-nfs:/avatar-models/` (manual or CI) |
| **Register** | Add model path to `AllowedAvatarModels` in Go and JS allowlists, commit to repo |
| **Deploy** | Flux rolls out updated companions-frontend config; model already available on NFS PVC — no image rebuild needed |
| **CDN sync** | CronJob `rclone sync` from gravenhollow RustFS `avatar-models` bucket → Cloudflare R2 `avatar-models` bucket |
### 5. Deployment and Storage Architecture
#### Local Serving (LAN users)
Companions-frontend currently serves VRM models via `http.FileServer(http.Dir("assets"))` from the container filesystem. This bakes models into the image and requires a rebuild to add new avatars.
The new approach mounts avatar models from gravenhollow via an `nfs-fast` PVC:
```yaml
# PersistentVolumeClaim for avatar models
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: avatar-models
namespace: ai-ml
spec:
storageClassName: nfs-fast
accessModes: [ReadOnlyMany]
resources:
requests:
storage: 10Gi
```
The pod mounts this PVC at `/models` and the Go server serves it at `/assets/models/`:
```go
// Replace embedded assets with NFS-backed volume
mux.Handle("/assets/models/", http.StripPrefix("/assets/models/",
http.FileServer(http.Dir("/models"))))
```
Benefits:
- **No image rebuild** to add/update models — write to gravenhollow NFS, pod sees it immediately (with `actimeo=600` cache, within 10 minutes)
- **All-SSD + dual 10GbE** — VRM files (typically 5–30 MB) load in <100ms on LAN
- **ReadOnlyMany** — multiple replicas can share the same PVC
- Source `.blend` files and textures remain on Quobyte S3 (Kasm bucket) for the creation workflow; only promoted VRM exports land on gravenhollow
#### Remote Serving (Cloudflare R2 CDN)
Companions-chat is accessed externally via Cloudflare Tunnel → `envoy-internal`. Serving multi-MB VRM files through the tunnel works but adds latency and consumes tunnel bandwidth. Cloudflare R2 provides a better path:
| | |
|---|---|
| **Bucket** | `avatar-models` on Cloudflare R2 |
| **Custom domain** | `assets.daviestechlabs.io` (Cloudflare DNS, orange-clouded) |
| **Free egress** | R2 has zero egress fees — ideal for large binary assets |
| **Cache** | Cloudflare CDN caches at 300+ global PoPs; `Cache-Control: public, max-age=31536000, immutable` |
| **Sync** | CronJob in cluster: `rclone sync gravenhollow-s3:avatar-models r2:avatar-models --checksum` |
| **Auth** | Public read (models are not sensitive); write via R2 API token in Vault |
##### R2 Sync CronJob
```yaml
apiVersion: batch/v1
kind: CronJob
metadata:
name: avatar-models-r2-sync
namespace: ai-ml
spec:
schedule: "0 */6 * * *" # Every 6 hours
jobTemplate:
spec:
template:
spec:
containers:
- name: sync
image: rclone/rclone:1.68
command:
- rclone
- sync
- gravenhollow-s3:avatar-models
- r2:avatar-models
- --checksum
- --transfers=4
- -v
volumeMounts:
- name: rclone-config
mountPath: /config/rclone
readOnly: true
volumes:
- name: rclone-config
secret:
secretName: rclone-r2-config
restartPolicy: OnFailure
```
##### rclone Config (ExternalSecret from Vault)
```ini
[gravenhollow-s3]
type = s3
provider = Other
endpoint = https://gravenhollow.lab.daviestechlabs.io:30292
access_key_id = <from-vault>
secret_access_key = <from-vault>
[r2]
type = s3
provider = Cloudflare
endpoint = https://<account-id>.r2.cloudflarestorage.com
access_key_id = <from-vault>
secret_access_key = <from-vault>
region = auto
```
##### Client-Side Routing
The frontend detects whether the user is on LAN or remote and routes model fetches accordingly:
```javascript
// avatar.js — model URL resolution
function resolveModelURL(path) {
// LAN users: serve from the Go server (NFS-backed, same origin)
// Remote users: serve from Cloudflare R2 CDN
const isLAN = location.hostname.endsWith('.lab.daviestechlabs.io');
if (isLAN) return path; // e.g. /assets/models/Companion-A.vrm
return `https://assets.daviestechlabs.io${path.replace('/assets', '')}`;
// → https://assets.daviestechlabs.io/models/Companion-A.vrm
}
```
Alternatively, the Go server can set the model base URL via a template variable based on the `Host` header, keeping the logic server-side.
#### Versioning Strategy
VRM files are immutable once promoted — updated models get a new filename (e.g., `Companion-A-v2.vrm`) rather than overwriting. This ensures:
- Cloudflare CDN cache never serves stale content
- Rollback is trivial — point the allowlist back to the previous version
- Browser `Cache-Control: immutable` works correctly
#### Storage Tier Summary
| Location | Purpose | Tier | Access |
|----------|---------|------|--------|
| Quobyte S3 (`kasm` bucket) | Working files: `.blend`, textures, WIP exports | Kasm rclone volume | Kasm sessions only |
| gravenhollow NFS (`/avatar-models/`) | Production VRM models + animations | `nfs-fast` PVC (RO) | companions-frontend pod, LAN |
| gravenhollow RustFS S3 (`avatar-models`) | Mirror of NFS dir for R2 sync source | S3 API | CronJob rclone |
| Cloudflare R2 (`avatar-models`) | CDN-served copy for remote users | R2 public bucket | Global, zero egress fees |
## BlenderMCP Capabilities Used
| MCP Tool | Avatar Workflow Use |
|----------|-------------------|
| `get_scene_info` | Inspect current scene before modifications |
| `create_object` | Scaffold base meshes for characters |
| `modify_object` | Adjust proportions, positions, bone placement |
| `set_material` | Apply skin, hair, clothing materials |
| `execute_blender_code` | Run VRM export scripts, batch operations, custom rigging |
| `get_screenshot` | AI reviews viewport to understand current state |
| `poly_haven_download` | Fetch HDRIs, textures for environment/materials |
| `hyper3d_generate` | Generate base 3D models from text prompts via Hyper3D Rodin |
## Security Considerations
* **Code execution:** BlenderMCP's `execute_blender_code` runs arbitrary Python in Blender. The Kasm session is sandboxed (DinD container with no cluster access), limiting blast radius. Always save before executing AI-generated code.
* **Telemetry:** BlenderMCP collects anonymous telemetry by default. Disabled via `DISABLE_TELEMETRY=true` in the MCP server config.
* **Network:** The TCP socket (port 9876) between the MCP server and Blender add-on is local to the session. If accessed remotely, ensure the connection is tunnelled or restricted.
* **S3 credentials:** rclone volume plugin credentials are managed via Kasm storage mappings and the existing `kasm-agent` ExternalSecret — no new secrets required.
* **R2 credentials:** Cloudflare R2 API token stored in Vault (`kv/data/cloudflare-r2`), accessed via ExternalSecret by the sync CronJob. Write-only scope — the CronJob uploads but cannot delete the bucket.
* **Public R2 bucket:** Avatar models are public assets (served to any authenticated companions-chat user). No sensitive data in VRM files. R2 bucket is read-only public via custom domain; write access requires the API token.
* **Model allowlist:** Even though models are served from NFS/R2, the server-side and client-side allowlists in companions-frontend gate which models users can actually select. Uploading a VRM to gravenhollow does not make it available without a code change.
## Pros and Cons of the Options
### Option 1 — BlenderMCP in Kasm + VS Code + Quobyte S3 + gravenhollow NFS + Cloudflare R2
* Good, because AI-assisted modelling reduces manual effort for avatar creation
* Good, because assets persist in S3 across sessions and are accessible from CI
* Good, because no new infrastructure — Kasm, rclone, Quobyte, gravenhollow, and Cloudflare are already deployed
* Good, because VS Code MCP integration means one editor for code and 3D work
* Good, because Kasm sandboxes Blender execution away from the cluster
* Good, because NFS-fast serving decouples model assets from container images (no rebuild to add models)
* Good, because Cloudflare R2 has zero egress fees and global CDN caching for remote users
* Good, because immutable versioned filenames enable aggressive caching and trivial rollback
* Bad, because BlenderMCP is a third-party tool with arbitrary code execution
* Bad, because socket communication adds latency for remote Kasm sessions
* Bad, because VRM rigging quality may require manual adjustment after AI scaffolding
* Bad, because two-hop promotion path adds operational complexity
### Option 2 — Local Blender + BlenderMCP on developer laptop
* Good, because lowest latency (everything local)
* Good, because no Kasm dependency
* Bad, because assets are local — no durable S3 storage without manual sync
* Bad, because Blender + add-ons must be installed on every dev machine
* Bad, because not reproducible across machines
### Option 3 — Hyper3D / Rodin cloud generation only
* Good, because no Blender installation needed
* Good, because fully prompt-driven model generation
* Bad, because limited control over output — no fine-tuning materials, rigging, or proportions
* Bad, because Hyper3D free tier has daily generation limits
* Bad, because generated models require post-processing for VRM compliance (humanoid rig, expressions, visemes)
* Bad, because vendor dependency for a core asset pipeline
### Option 4 — Manual Blender workflow (status quo)
* Good, because full manual control
* Good, because no new tooling
* Bad, because slow — no AI assistance for repetitive modelling tasks
* Bad, because no integration with the development workflow
* Bad, because assets stored ad-hoc with no structured pipeline to companions-frontend
## Links
* Related to [ADR-0046](0046-companions-frontend-architecture.md) (companions-frontend architecture — Three.js + VRM avatars)
* Related to [ADR-0026](0026-storage-strategy.md) (storage strategy — gravenhollow NFS-fast, Quobyte S3, rclone)
* Related to [ADR-0044](0044-dns-and-external-access.md) (DNS and external access — Cloudflare Tunnel, split-horizon)
* Related to [ADR-0049](0049-self-hosted-productivity-suite.md) (Kasm Workspaces)
* [BlenderMCP GitHub](https://github.com/ahujasid/blender-mcp)
* [VRM Add-on for Blender](https://vrm-addon-for-blender.info/en/)
* [VRM Specification](https://vrm.dev/en/)
* [@pixiv/three-vrm](https://github.com/pixiv/three-vrm) (runtime loader used in companions-frontend)
* [Poly Haven](https://polyhaven.com/) (free 3D assets, HDRIs, textures)
* [Hyper3D Rodin](https://hyper3d.ai/) (AI 3D model generation)
* [Cloudflare R2 Documentation](https://developers.cloudflare.com/r2/)
* [Cloudflare R2 Custom Domains](https://developers.cloudflare.com/r2/buckets/public-buckets/#custom-domains)