- Add BGE embedding model config (port 8002) to litellm-config.yaml
- Add GPU_VLLM_EMBED_URL env var to compose and .env
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Remove crawl4ai service from ai/compose.yaml (will use local MCP instead)
- Remove crawl4ai backup volume from core/compose.yaml
- Add core/backrest/config.json (infrastructure as code)
- Change backrest from volume to bind-mounted config
- Update CLAUDE.md and README.md documentation
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Supervisor XML-RPC API v3.0 (Supervisor 4.3.0) only supports 2-parameter
readLog(offset, length) calls, not 3-parameter calls with filename.
The SUPERVISOR_LOGFILE environment variable is not used by the API.
Testing showed:
- Working: server.supervisor.readLog(-4096, 0)
- Failing: server.supervisor.readLog(-4096, 4096, '/path/to/log')
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Replaced nginx:alpine proxy with dev.pivoine.art/valknar/supervisor-ui:latest
- Modern Next.js UI with real-time SSE updates, batch operations, and charts
- Changed service port from 80 (nginx) to 3000 (Next.js)
- Removed supervisor-nginx.conf (no longer needed)
- Kept same URL (supervisor.ai.pivoine.art) and Authelia SSO protection
- Added health check for /api/health endpoint
- Service connects to RunPod Supervisor via Tailscale (SUPERVISOR_HOST/PORT)
- Replace orchestrator routing with direct vLLM server connections
- Qwen 2.5 7B on port 8000 (GPU_VLLM_QWEN_URL)
- Llama 3.1 8B on port 8001 (GPU_VLLM_LLAMA_URL)
- Simplify architecture by removing orchestrator proxy layer
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Replace GPU_TAILSCALE_IP interpolation with GPU_VLLM_API_URL
- LiteLLM requires full URL in api_base with os.environ/ syntax
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Replace COMFYUI_BACKEND_HOST and SUPERVISOR_BACKEND_HOST with GPU_TAILSCALE_IP
- Update LiteLLM config to use os.environ/GPU_TAILSCALE_IP for vLLM models
- Add GPU_TAILSCALE_IP env var to LiteLLM service
- Configure qwen-2.5-7b and llama-3.1-8b to route through orchestrator
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Remove hardcoded default values from compose.yaml
- Backend IPs now managed via environment variables only
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Add nginx reverse proxy service for Supervisor web UI at supervisor.ai.pivoine.art with Authelia authentication. Proxies to RunPod GPU instance via Tailscale (100.121.199.88:9001).
Changes:
- Create supervisor-nginx.conf for nginx proxy configuration
- Add supervisor service to docker-compose with Traefik labels
- Add supervisor.ai.pivoine.art to Authelia protected domains
- Remove deprecated Flux-related files
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Replace hardcoded IP in comfyui-nginx.conf with env vars
- Add COMFYUI_BACKEND_HOST and COMFYUI_BACKEND_PORT to compose.yaml
- Use envsubst to substitute variables at container startup
- Defaults: 100.121.199.88:8188 (current RunPod Tailscale IP)
- Add ComfyUI service to AI stack using nginx:alpine as reverse proxy
- Proxy to RunPod ComfyUI via Tailscale (100.121.199.88:8188)
- Configure Traefik routing for comfy.ai.pivoine.art
- Enable Authelia SSO middleware (net-authelia)
- Support WebSocket connections for real-time updates
- Set appropriate timeouts for image generation (300s)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Set drop_params: false in litellm_settings
- Set modify_params: false in litellm_settings
- Set drop_params: false in default_litellm_params
- Commented out LITELLM_DROP_PARAMS env var
- Removed --drop_params command flag
These settings were stripping critical streaming parameters causing
vLLM streaming responses to collapse into empty deltas
- Reverted direct orchestrator connection to WebUI
- Added stream: true parameter to qwen-2.5-7b model config
- Keep LiteLLM as single proxy for all models
- Configure WebUI with both LiteLLM and direct orchestrator API base URLs
- This bypasses LiteLLM's streaming issues for the qwen-2.5-7b model
- WebUI will now show models from both endpoints
- Allows testing if LiteLLM is the bottleneck for streaming
Related to streaming fix in RunPod models/vllm/server.py
- Changed back from hosted_vllm/qwen-2.5-7b to openai/qwen-2.5-7b
- Removed /v1 suffix from api_base (LiteLLM adds it automatically)
- Added supports_system_messages: false for vLLM compatibility
- Update api_base URLs from 100.100.108.13 to 100.121.199.88 (RunPod Tailscale IP)
- All self-hosted models (qwen-2.5-7b, flux-schnell, musicgen-medium) now route through Tailscale VPN
- Tested and verified connectivity between VPS and RunPod GPU orchestrator
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Removed outdated AI infrastructure README that referenced GPU services.
VPS AI services (Open WebUI, Crawl4AI, facefusion) are documented in compose.yaml comments.
GPU infrastructure docs are now in dedicated runpod repository.
