docs/api.md

API

FastAPI endpoints cover environment lifecycle, orchestration, policy inference, evaluation, training metrics, case retrieval, and evidence queries.

Product Inference

• POST /policy/infer selects one legal candidate using the active Transformers model when available, with deterministic safety-ranker fallback.
• GET /policy/model_status reports active-model configuration and load status.

The active model is controlled by checkpoints/active/active_model_manifest.json, generated by scripts/activate_sweep_model.py. The default production path prefers the GRPO adapter for qwen-qwen2-5-0-5b-instruct, then falls back to the merged Qwen 0.5B artifact or SFT adapter if required.

Example:

curl http://127.0.0.1:8200/policy/model_status
curl -X POST http://127.0.0.1:8200/policy/infer