"""The docker deployment must run auxiliary calls on a small model.

Latency win: intent judging, tool routing and arg extraction are
classification/JSON calls, not the spoken answer. Running them on a small fast
model means the big chat model only runs once per command (for the answer),
instead of 2-3 times per command for routing/extraction too.

The wiring is: docker/jarvis-config.template.json renders `intent_judge_model`
from `${OLLAMA_INTENT_MODEL}`, and the reply engine's resolver falls through
`tool_router_model -> intent_judge_model -> ollama_chat_model`. The template
sets no `tool_router_model`, so the auxiliary model is whatever
`OLLAMA_INTENT_MODEL` renders to. These tests pin that behaviour end to end.
"""

import json
import string
from pathlib import Path

import pytest

from jarvis.reply.engine import resolve_tool_router_model

TEMPLATE = Path(__file__).resolve().parent.parent / "docker" / "jarvis-config.template.json"


def _render(**env) -> dict:
    raw = TEMPLATE.read_text(encoding="utf-8")
    return json.loads(string.Template(raw).safe_substitute(**env))


class _Cfg:
    """cfg stand-in carrying only the fields the resolver reads. The template
    does not render `tool_router_model`, so it stays empty here too."""

    def __init__(self, rendered: dict):
        self.tool_router_model = rendered.get("tool_router_model", "") or ""
        self.intent_judge_model = rendered.get("intent_judge_model", "") or ""
        self.ollama_chat_model = rendered.get("ollama_chat_model", "") or ""


def test_template_renders_separate_intent_model():
    cfg = _render(OLLAMA_CHAT_MODEL="qwen3:8b", OLLAMA_INTENT_MODEL="qwen2.5:3b")
    assert cfg["ollama_chat_model"] == "qwen3:8b"
    assert cfg["intent_judge_model"] == "qwen2.5:3b"
    assert cfg["intent_judge_model"] != cfg["ollama_chat_model"]


@pytest.mark.unit
def test_aux_calls_route_to_small_model_not_chat_model():
    """The whole point: with a big chat model and a small intent model, tool
    routing must resolve to the small model, leaving the big model for answers."""
    cfg = _Cfg(_render(OLLAMA_CHAT_MODEL="qwen3:8b", OLLAMA_INTENT_MODEL="qwen2.5:3b"))
    assert resolve_tool_router_model(cfg) == "qwen2.5:3b"


@pytest.mark.unit
def test_folding_intent_onto_chat_model_keeps_one_model():
    """Setting OLLAMA_INTENT_MODEL == OLLAMA_CHAT_MODEL folds everything back
    onto a single resident model (the documented VRAM-saving opt-out)."""
    cfg = _Cfg(_render(OLLAMA_CHAT_MODEL="qwen2.5:3b", OLLAMA_INTENT_MODEL="qwen2.5:3b"))
    assert resolve_tool_router_model(cfg) == "qwen2.5:3b"
    assert cfg.intent_judge_model == cfg.ollama_chat_model