m2-market/scout/tests/test_scout.py

from __future__ import annotations

import importlib.util
import json
import sys
from pathlib import Path

import httpx
import pytest


PLUGIN = Path(__file__).resolve().parents[1] / "plugin" / "m2-solution-scout" / "__init__.py"


@pytest.fixture()
def scout(monkeypatch, tmp_path):
    spec = importlib.util.spec_from_file_location("m2_solution_scout_test", PLUGIN)
    module = importlib.util.module_from_spec(spec)
    sys.modules[spec.name] = module
    assert spec.loader is not None
    spec.loader.exec_module(module)
    monkeypatch.setattr(module, "STATE_PATH", tmp_path / "state.json")
    monkeypatch.setattr(module, "STATE_DIR", tmp_path)
    monkeypatch.setattr(module, "OUTBOX_DIR", tmp_path / "outbox")
    return module


def policy(scout):
    return {
        "enabled": True,
        "desktop_id": "chris-m2o",
        "operator_id": "op_chris",
        "tenant_id": "machine-machine",
        "min_score": 0.78,
        "min_coverage": 0.2,
        "max_proposals_per_day": 5,
        "max_proposals_per_session": 1,
        "proposal_cooldown_minutes": 45,
        "summary": {
            "max_source_chars": 12000,
            "max_summary_chars": 120,
            "redact_client_identifiers": True,
        },
        "catalog": {
            "memory_api_url": "https://memory.test",
            "agent_id": "market:catalog",
            "limit": 5,
            "routing_strategy": "standard",
        },
        "store": {"deeplink_scheme": "m2store"},
    }


def test_gate_disabled_opted_out_rate_capped_and_cooldown_noop(scout):
    enabled = policy(scout)
    assert scout.gate({"enabled": False}, {}, session_id="s1") == (False, "disabled")
    assert scout.load_policy(Path("/no/such/file")) == {
        "enabled": False,
        "reason": "disabled_or_missing_tenant",
    }
    today = scout._utcnow().date().isoformat()
    assert scout.gate(
        enabled,
        {"daily": {today: 5}, "sessions": {}, "last_proposal_at": None},
        session_id="s1",
    ) == (False, "rate_capped")
    assert scout.gate(
        enabled,
        {"daily": {}, "sessions": {"s1": 1}, "last_proposal_at": None},
        session_id="s1",
    ) == (False, "session_capped")
    assert scout.gate(
        enabled,
        {"daily": {}, "sessions": {}, "last_proposal_at": scout._iso()},
        session_id="s1",
    ) == (False, "proposal_cooldown")


def test_policy_refuses_raw_sources(scout, tmp_path):
    path = tmp_path / "pull-policy.toml"
    path.write_text(
        """
[scout]
enabled = true
tenant_id = "machine-machine"

[scout.sources]
raw_keystrokes = true
raw_client_data = false
""",
        encoding="utf-8",
    )
    with pytest.raises(scout.PolicyError):
        scout.load_policy(path)


def test_redaction_and_summary_are_bounded(scout):
    text = (
        "Use sk-abcdefghijklmnopqrstuvwxyz and API_KEY=supersecretvalue for jane@example.com. "
        "Build a competitor research report with sources and PDF output."
    )
    summary = scout.summarize_turn(text, "Prepare the report.", policy(scout))
    assert "sk-" not in summary["summary"]
    assert "supersecretvalue" not in summary["summary"]
    assert "jane@example.com" not in summary["summary"]
    assert "[REDACTED_SECRET]" in summary["summary"]
    assert len(summary["summary"]) <= 120
    assert summary["schema_version"] == "m2.scout.intent_summary.v1"


def test_proposal_outbox_record_shape_matches_schema(scout, tmp_path):
    p = policy(scout)
    summary = scout.summarize_turn("competitor research report pdf", "", p)
    match = {
        "listing_id": "lst_competitor-scan",
        "solution_id": "sol_competitor-scan",
        "score": 0.84,
        "coverage": 0.72,
        "listing": {
            "name": "Competitor Scan",
            "summary": "Research report package.",
            "price": {"amount": 40, "currency": "m2cr", "model": "fixed"},
            "stats": {"installs": 12, "rating": 4.6},
        },
    }
    proposal = scout.build_proposal(match, summary, p)
    event = scout.write_proposal_shown(proposal, tmp_path / "outbox")
    assert event["event_type"] == "proposal_shown"
    assert event["proposal"]["schema_version"] == "m2.scout.proposal.v1"
    assert event["proposal"]["listing"]["listing_id"] == "lst_competitor-scan"
    assert event["proposal"]["deeplink"].startswith("m2store://listing/lst_competitor-scan")
    lines = list((tmp_path / "outbox").glob("*.jsonl"))[0].read_text(encoding="utf-8").splitlines()
    assert json.loads(lines[0])["proposal_id"] == event["proposal_id"]


def test_mocked_catalog_search_filters_visibility_and_posts_live_shape(scout, monkeypatch):
    requests = []

    def handler(request: httpx.Request) -> httpx.Response:
        requests.append(json.loads(request.content.decode("utf-8")))
        return httpx.Response(
            200,
            json={
                "results": [
                    {
                        "score": 0.91,
                        "metadata": {
                            "listing_id": "lst_competitor-scan",
                            "listing": {
                                "name": "Competitor Scan",
                                "summary": "Competitor research report with PDF output",
                                "keywords": ["competitor", "research", "report"],
                                "tenant_visibility": ["*"],
                                "status": "published",
                            },
                        },
                    },
                    {
                        "score": 0.99,
                        "metadata": {
                            "listing_id": "lst_private",
                            "listing": {
                                "name": "Private",
                                "tenant_visibility": ["other-tenant"],
                                "status": "published",
                            },
                        },
                    },
                ],
                "routing": {},
            },
        )

    original_init = httpx.Client.__init__

    def patched_init(self, *args, **kwargs):
        kwargs["transport"] = httpx.MockTransport(handler)
        original_init(self, *args, **kwargs)

    monkeypatch.setattr(httpx.Client, "__init__", patched_init)
    summary = scout.summarize_turn("competitor research report pdf", "", policy(scout))
    results = scout.search_catalog(summary, policy(scout))
    assert requests[0]["agent_id"] == "market:catalog"
    assert requests[0]["query"] == summary["summary"]
    assert "tenant_id" not in requests[0]
    assert [item["listing_id"] for item in results] == ["lst_competitor-scan"]