import pytest

from aiatlas.connectors.labs.cohere import BLOG, DOCS, CohereConnector, blog_items
from aiatlas.sdk.facts import Target
from tests.conftest import claims_of, entity_names, extract_from_fixture, fixture_path


@pytest.fixture
def connector() -> CohereConnector:
    return CohereConnector()


async def test_models(connector):
    facts = await extract_from_fixture(connector, Target(url=f"{DOCS}.md", doc_type="model_docs", key="models"), fixture_path("cohere", "models.md"), content_type="text/markdown")
    models = entity_names(facts, "model")
    assert len(models) >= 40 and {"command-a-plus-05-2026", "embed-v4.0", "rerank-v4.0-pro", "parse-v5.0", "cohere-transcribe-03-2026", "tiny-aya-global"} <= models
    a_plus = claims_of(facts, "command-a-plus-05-2026")
    assert a_plus["context_length"] == 128_000 and a_plus["max_output_tokens"] == 64_000 and a_plus["status"] == "active"
    assert a_plus["modalities"] == ["image", "text"] and a_plus["vision"] is True and a_plus["family"] == "Command" and a_plus["is_moe"] is True   # canonical, sorted
    a_plus_ref = next(e for e in facts.entities if e.name == "command-a-plus-05-2026")
    assert a_plus_ref.family is not None and a_plus_ref.family.entity_type == "model_family" and a_plus_ref.family.name == "Command"
    assert a_plus["foundry_model_id"] == "coherelabs-command-a-plus-05-2026-w4a4"
    r = claims_of(facts, "command-r-03-2024")
    assert r["status"] == "deprecated" and r["deprecation_date"] == "2025-09-15"
    embed = claims_of(facts, "embed-v4.0")
    assert embed["context_length"] == 128_000 and 1536 in embed["embedding_dimensions"] and embed["modalities_output"] == ["embedding"]
    north = claims_of(facts, "north-small-translate-1-0")
    assert north["parameter_count"] == 218_000_000_000 and north["active_parameter_count"] == 25_000_000_000 and north["is_moe"] is True
    assert claims_of(facts, "rerank-v3.5")["bedrock_model_id"] == "cohere.rerank-v3-5:0"
    transcribe = claims_of(facts, "cohere-transcribe-03-2026")
    assert transcribe["openness"] == "open-weights" and transcribe["openness_raw"] == "open-source" and transcribe["weights_available"] is True   # prose "open source" → canonical category
    assert claims_of(facts, "command-a-reasoning-08-2025")["reasoning"] is True
    # alias rows fold into the model they point at
    plus = next(e for e in facts.entities if e.name == "command-r-plus-04-2024")
    assert "command-r-plus" in plus.aliases and "command-r-plus" not in models
    assert plus.identifiers == {"cohere_model_id": "command-r-plus-04-2024"}
    plus_claims = claims_of(facts, "command-r-plus-04-2024")
    assert plus_claims["api_aliases"] == ["command-r-plus"] and plus_claims["api_alias"] == "command-r-plus"        # always a list + first for compat
    assert sum(r.predicate == "available_through" for r in facts.relations) >= 30


async def test_blog(connector):
    facts = await extract_from_fixture(connector, Target(url=BLOG, doc_type="listing", key="blog"), fixture_path("cohere", "blog.html"))
    events = {e.source_url: e for e in facts.events}
    assert len(events) >= 20
    north = events[f"{BLOG}/north-small-translate"]
    assert north.summary.startswith("Cohere: Introducing North Small Translate") and north.effective_at.date().isoformat() == "2026-09-10"
    assert north.category == "release" and north.meta["categories"] == ["Product Launch"]
    assert events[f"{BLOG}/command-a-plus"].effective_at.date().isoformat() == "2026-05-20"
    assert all(e.effective_at is not None for e in facts.events)
    assert any(t.needs_llm for t in facts.targets)


def test_blog_items_direct():
    items = blog_items(fixture_path("cohere", "blog.html").read_bytes())
    assert items[0].url == f"{BLOG}/north-small-translate" and items[0].published_at is not None
    assert all(not it.url.startswith(f"{BLOG}/tag/") for it in items)