Scan a directory recursively for runnable .gguf model files (skipping mmproj-* projector files). Returns name, path, size, a quant guess from the filename, and sharded-set detection.

Report all llama-server processes bellows is supervising (pid, port, model, uptime) and optionally probe a specific port's /health endpoint, including servers bellows does not own.

Spawn llama-server for a model (full arg validation, no shell), wait for its /health endpoint to report ready, and record the pid under bellows supervision. Refuses to start if the port is already in use.

Gracefully stop (SIGTERM, then SIGKILL after a grace period) a llama-server that bellows started. Refuses to touch processes it does not own.

Send a batch of chat prompts to a running llama-server over its OpenAI-compatible API and report each response with latency and generation speed (tokens/second as measured by llama.cpp).

Read-only queries against the crucible eval results database: list runs for a model, summarize one run per category (pass rates plus complied/hedged/refused tallies), or compare two runs.