"""Ollama Cloud provider profile with reasoning_effort forwarding.

Ollama Cloud (ollama.com) provides an OpenAI-compatible API that accepts
a top-level ``reasoning_effort`` parameter with values: high, medium, low,
max, none.  The API rejects undocumented values like "xhigh".

This profile overrides :meth:`build_api_kwargs_extras` to forward the
configured effort level, clamping xhigh → high (ollama.com has no xhigh;
its "max" is heavier than "high" and typically overkill).

Deploy to: /opt/data/plugins/model-providers/ollama-cloud/__init__.py
User plugins load after bundled ones with last-writer-wins, so this
overrides the bare ProviderProfile stub that ships with the gateway image.
"""

from __future__ import annotations

from typing import Any

from providers import register_provider
from providers.base import ProviderProfile

# Valid reasoning_effort values per ollama.com API
_OLLAMA_VALID_EFFORTS = frozenset({"high", "medium", "low", "max", "none"})


class OllamaCloudProfile(ProviderProfile):
    """Ollama Cloud — top-level reasoning_effort forwarding."""

    def build_api_kwargs_extras(
        self, *, reasoning_config: dict | None = None, model: str | None = None, **context
    ) -> tuple[dict[str, Any], dict[str, Any]]:
        top_level: dict[str, Any] = {}

        if not isinstance(reasoning_config, dict):
            return {}, top_level

        effort = (reasoning_config.get("effort") or "").strip().lower()

        # xhigh → high (not max; max is too heavy for routine use)
        if effort == "xhigh":
            effort = "high"

        if effort in _OLLAMA_VALID_EFFORTS:
            top_level["reasoning_effort"] = effort

        return {}, top_level


ollama_cloud = OllamaCloudProfile(
    name="ollama-cloud",
    aliases=("ollama_cloud",),
    default_aux_model="nemotron-3-nano:30b",
    env_vars=("OLLAMA_API_KEY",),
    base_url="https://ollama.com/v1",
)

register_provider(ollama_cloud)