Tinker SDK Backend
The Tinker backend uses Tinker’s hosted inference and training APIs. No local GPU is required. Training runs against Qwen/Qwen3-30B-A3B via API credits.
Requirements
Installation
Clone and install
git clone https://github.com/kfallah/CLaaS.git
cd CLaaS
uv sync --extra tinker
Configure environment
cd docker
cp .env.tinker.example .env.tinker
.env.tinker and set TELEGRAM_BOT_TOKEN and TINKER_API_KEY.Start the stack
docker compose -f docker-compose.tinker.yml --env-file .env.tinker up --build
Verify
curl http://localhost:8000/v1/models
curl http://localhost:8080/
curl http://localhost:8080/v1/lora
Services
| Service | Port | Description |
|---|
tinker-proxy | 8000 | OpenAI-compatible proxy backed by Tinker SDK |
claas-api | 8080 | CLaaS feedback API in Tinker execution mode |
openclaw | 18789 | OpenClaw gateway with Telegram bot |
init | — | One-shot: creates LoRA via API + writes OpenClaw config |
Configuration
These variables are set in .env.tinker.
| Variable | Required | Default | Description |
|---|
TELEGRAM_BOT_TOKEN | Yes | — | Bot token from @BotFather |
TINKER_API_KEY | Yes | — | Tinker SDK API key |
MODEL | No | Qwen/Qwen3-30B-A3B | Base model (must use Tinker name) |
FEEDBACK_BATCH_SIZE | No | 4 | Samples per batch before distill |
Known Gotchas
Tinker model naming: Tinker uses its own model identifiers that differ from HuggingFace names. For example, the HuggingFace model Qwen/Qwen3-Coder-30B-A3B-Instruct is Qwen/Qwen3-30B-A3B in Tinker. Sampling works with either name, but LoRA training init will reject the HuggingFace name with a 400 error. Always use the Tinker name.
CLAAS_TINKER_BASE_MODEL must match base_model: The proxy reads CLAAS_TINKER_BASE_MODEL to initialize its sampling client, and the eval config’s base_model is passed to the API for LoRA init. If they reference different models, scoring and training will target different models.
