Decisions API

curl -s http://localhost:8080/v1/decisions \
  -H "Authorization: Bearer $GOMODEL_MASTER_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-6-luna",
    "input": "Shoes arrived two weeks late and in the wrong size. Also I see two charges on my card.",
    "questions": [
      {"type": "predicate", "name": "escalate", "instructions": "Does this need urgent human attention?"},
      {"type": "choice", "name": "department", "instructions": "Which team should handle this?",
       "choices": [{"value": "returns", "description": "Exchanges, wrong items"},
                   {"value": "shipping", "description": "Delivery status, delays"},
                   {"value": "billing", "description": "Charges, invoices"}]},
      {"type": "score", "name": "frustration", "instructions": "How frustrated is the customer?",
       "levels": [{"label": "Calm"}, {"label": "Frustrated"}, {"label": "Very angry"}]}
    ]
  }'

{
  "model": "gpt-6-luna",
  "answers": [
    {"name": "escalate", "type": "predicate", "probability": 0.93},
    {"name": "department", "type": "choice", "choice": "returns", "confidence": 0.21,
     "probabilities": [{"value": "returns", "probability": 0.47}, {"value": "shipping", "probability": 0.28},
                       {"value": "billing", "probability": 0.25}]},
    {"name": "frustration", "type": "score", "score": 1.44, "confidence": 0.78,
     "probabilities": [{"label": "Calm", "probability": 0.0, "value": 0},
                       {"label": "Frustrated", "probability": 0.56, "value": 1},
                       {"label": "Very angry", "probability": 0.44, "value": 2}]}
  ],
  "usage": {"input_tokens": 101, "input_tokens_details": {"cache_write_tokens": 0, "cached_tokens": 0},
            "output_tokens": 0, "output_tokens_details": {"reasoning_tokens": 0}, "total_tokens": 101}
}

from openai import OpenAI

client = OpenAI(api_key="change-me", base_url="http://localhost:8080/v1")
decision = client.decisions.create(
    model="jev/jev-latest",  # lub openai/gpt-6-luna
    input="I was charged twice. Please fix this ASAP.",
    questions=[{"type": "predicate", "name": "billing", "instructions": "Is this ticket about billing?"}],
)
print(decision.answers[0].probability)

virtual_models:
  - source: classifier
    strategy: failover
    targets:
      - { model: kev/kev-latest }     # najpierw lokalny Kev
      - { model: openai/gpt-6-luna }  # OpenAI, gdy Kev nie działa, oraz dla obrazów