Architecture

{
  "turn": 2,
  "observation": {
    "role": "assistant",
    "content": "I've been having this pain in my lower back..."
  },
  "reward": 0.75,
  "scores": {
    "D1_InformationGathering": 0.8,
    "D2_GoalProgress": 0.7
  },
  "episode_complete": false
}

# POST /api/v1/episodes → Submit turns → Collect rewards
episode = post("/api/v1/episodes", {"collection_slug": "...", "scenario_slug": "..."})
while not done:
    action = model.generate(observation)
    result = post(f"/api/v1/episodes/{episode_id}/turns", {"messages": [...]})
    train_on_reward(result["reward"])

# POST /api/v1/evaluate → Get single reward
result = post("/api/v1/evaluate", {
    "collection_slug": "...",
    "scenario_slug": "...",
    "messages": [...]
})
reward = result["reward"]

# POST /api/v1/batch/evaluate → Get rewards for all
result = post("/api/v1/batch/evaluate", {"items": [...]})
rewards = [r["reward"] for r in result["results"]]

# POST /api/v1/compare → Get preference signal
result = post("/api/v1/compare", {
    "collection_slug": "...",
    "scenario_slug": "...",
    "response_a": {"messages": [...]},
    "response_b": {"messages": [...]}
})
winner = result["winner"]  # 'a', 'b', or 'tie'
margin = result["margin"]  # reward difference (useful for DPO)