#!/usr/bin/env bash
# Policy server: vLLM serving LiquidAI/LFM2.5-2.6B on GPU 1.
#
# Flag provenance:
#   --return-tokens-as-token-ids     capture proxy needs the exact sampled token ids
#   --logprobs-mode processed_logprobs  proxy needs per-token logprobs that match the policy
#   --weight-transfer-config         TRL AsyncGRPOTrainer pushes merged weights over NCCL
#   VLLM_SERVER_DEV_MODE=1           exposes the weight-update endpoint TRL posts to
#
# Deliberately NOT passed:
#   --enable-lora                    adapter sync rotates adapter names, which the
#                                    OpenEnv capture proxy cannot address; the trainer
#                                    merges the LoRA into the base and syncs full weights
set -euo pipefail

MODEL="${MODEL:-LiquidAI/LFM2.5-2.6B}"
PORT="${PORT:-8001}"

CUDA_VISIBLE_DEVICES=1 VLLM_SERVER_DEV_MODE=1 \
vllm serve "$MODEL" \
    --port "$PORT" \
    --max-model-len 32768 \
    --return-tokens-as-token-ids \
    --logprobs-mode processed_logprobs \
    --enable-auto-tool-choice \
    --tool-call-parser lfm2 \
    --weight-transfer-config '{"backend":"nccl"}'