api/tests/test_classify_file.py

"""Unit tests for Step 1 file classification (_classify_file).

These tests call the real LLM so they require OPENAI_API_KEY / LLM env vars.
Run with: pytest tests/test_classify_file.py -v

To run a quick manual check against a real file without the full UI:
    python -m tests.test_classify_file <path/to/file.txt> [project_name...]
"""

from __future__ import annotations

import asyncio
import sys

import pytest

from app.core.agent_runner import _classify_file


# ── Fixtures ──────────────────────────────────────────────────────────────

PROJECTS_SAMPLE = [
    {
        "id": "aaaa-0001-0000-0000-000000000001",
        "name": "ARPA Sicilia POC",
        "status": "active",
        "aiSummary": "Proof of concept for AI features targeting ARPA Sicilia agency.",
    },
    {
        "id": "bbbb-0002-0000-0000-000000000002",
        "name": "SNAM AI Meeting Prep",
        "status": "active",
        "aiSummary": "AI-assisted preparation of meeting materials for SNAM.",
    },
    {
        "id": "cccc-0003-0000-0000-000000000003",
        "name": "SFERA+ Wave 2",
        "status": "active",
        "aiSummary": "Second wave of the SFERA+ whitelist project.",
    },
]

ARPA_EMAIL = """\
to: roberto.musso@hpe.com; luca.tondin@hpecds.com
isImportance: normal
hasAttachment: True
---
## Body
Buongiorno,

In riferimento alla riunione di ieri sul POC ARPA Sicilia, vi invio il riassunto
dei deliverable concordati:
- Preparare demo entro il 30 marzo
- Condividere documentazione tecnica con il team ARPA
- Fissare call di follow-up la prossima settimana

Cordiali saluti
Roberto Marchetti
"""

SNAM_EMAIL = """\
to: roberto.musso@hpe.com
isImportance: high
hasAttachment: False
---
## Body
Ciao,
ti invio l'agenda per la riunione SNAM di domani.
Per favore conferma la tua presenza.
"""

UNRELATED_EMAIL = """\
to: roberto.musso@hpe.com
isImportance: normal
---
## Body
Benvenuto nel programma HPE Employee Learning Series.
Completa la formazione richiesta entro la fine del trimestre.
"""


# ── Tests ─────────────────────────────────────────────────────────────────


@pytest.mark.asyncio
async def test_classify_arpa_matches_existing():
    project_id, domains, new_name = await _classify_file(
        file_path="arpa_email.txt",
        file_content=ARPA_EMAIL,
        projects=PROJECTS_SAMPLE,
        config_data_types=["tasks", "notes", "timelines"],
    )
    assert project_id == "aaaa-0001-0000-0000-000000000001", (
        f"Expected ARPA project, got project_id={project_id!r} new_name={new_name!r}"
    )
    assert new_name is None


@pytest.mark.asyncio
async def test_classify_snam_matches_existing():
    project_id, domains, new_name = await _classify_file(
        file_path="snam_email.txt",
        file_content=SNAM_EMAIL,
        projects=PROJECTS_SAMPLE,
        config_data_types=["tasks", "notes"],
    )
    assert project_id == "bbbb-0002-0000-0000-000000000002", (
        f"Expected SNAM project, got project_id={project_id!r} new_name={new_name!r}"
    )


@pytest.mark.asyncio
async def test_classify_unrelated_returns_new():
    project_id, domains, new_name = await _classify_file(
        file_path="learning_email.txt",
        file_content=UNRELATED_EMAIL,
        projects=PROJECTS_SAMPLE,
        config_data_types=["tasks", "notes"],
    )
    assert project_id == "new"
    assert new_name is not None  # LLM should suggest a name


@pytest.mark.asyncio
async def test_classify_empty_file_returns_new():
    project_id, domains, new_name = await _classify_file(
        file_path="empty.txt",
        file_content="   ",
        projects=PROJECTS_SAMPLE,
        config_data_types=["tasks"],
    )
    assert project_id == "new"


@pytest.mark.asyncio
async def test_classify_no_projects_returns_new():
    project_id, domains, new_name = await _classify_file(
        file_path="arpa_email.txt",
        file_content=ARPA_EMAIL,
        projects=[],
        config_data_types=["tasks", "notes"],
    )
    assert project_id == "new"
    assert new_name is not None


# ── CLI quick-test runner ─────────────────────────────────────────────────


async def _cli_test(file_path: str, project_names: list[str]) -> None:
    """Run Step 1 classification against a real file from the CLI."""
    import json
    from pathlib import Path

    content = Path(file_path).read_text(encoding="utf-8", errors="replace")
    projects = [
        {"id": f"test-id-{i:04d}", "name": name, "status": "active", "aiSummary": ""}
        for i, name in enumerate(project_names)
    ]

    print(f"\nClassifying: {file_path}")
    print(f"Projects in context: {[p['name'] for p in projects]}\n")

    project_id, domains, new_name = await _classify_file(
        file_path=file_path,
        file_content=content,
        projects=projects,
        config_data_types=["tasks", "notes", "timelines"],
    )

    result = {
        "project_id": project_id,
        "matched_name": next((p["name"] for p in projects if p["id"] == project_id), None),
        "new_project_name": new_name,
        "domains": domains,
    }
    print(json.dumps(result, indent=2, ensure_ascii=False))


if __name__ == "__main__":
    if len(sys.argv) < 2:
        print("Usage: python -m tests.test_classify_file <file_path> [project_name ...]")
        sys.exit(1)
    asyncio.run(_cli_test(sys.argv[1], sys.argv[2:]))