Skip to content

~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted.

2.7 KB
Raw Blame
"""Raw context should spend parsing work only on retained research findings."""

import pytest

from local_deep_research.chat.context import ChatContextManager


@pytest.mark.parametrize("limit", [-20, -1, 0, 1, 5, 20, True, False])
def test_selected_findings_keep_slice_semantics_and_only_strip_retained_text(
    monkeypatch, limit
):
    messages = []
    for number in range(8):
        messages.extend(
            [
                {"role": "user", "content": f"Question [9] {number}"},
                {
                    "role": "assistant",
                    "research_id": str(number),
                    "content": f"Finding {number} [1]",
                },
                {
                    "role": "assistant",
                    "message_type": "step",
                    "research_id": "step",
                    "content": "Progress",
                },
                {"role": "assistant", "content": "No research attached"},
            ]
        )
    manager = ChatContextManager("window-work", messages)
    manager.MAX_FINDINGS_TO_INCLUDE = limit
    expected_numbers = list(range(8))[-limit:]
    calls = []
    original = ChatContextManager._strip_citation_markers

    def strip(self, text):
        calls.append(text)
        return original(self, text)

    monkeypatch.setattr(ChatContextManager, "_strip_citation_markers", strip)
    assert manager._extract_findings_from_history() == "\n\n---\n\n".join(
        f"Finding {number}" for number in expected_numbers
    )
    assert calls == [f"Finding {number} [1]" for number in expected_numbers]
    assert messages[0]["content"] == "Question [9] 0"


def test_positive_window_does_not_walk_the_discarded_history():
    class Message(dict):
        role_reads = 0

        def get(self, key, *args):
            if key == "role":
                Message.role_reads += 1
            return super().get(key, *args)

    messages = []
    for number in range(500):
        messages.extend(
            [
                Message(role="user", content="Question"),
                Message(
                    role="assistant",
                    research_id=str(number),
                    content=f"Finding {number}",
                ),
            ]
        )
    manager = ChatContextManager("bounded-window", messages)
    Message.role_reads = 0
    assert manager._extract_findings_from_history().split("\n\n---\n\n") == [
        f"Finding {number}" for number in range(495, 500)
    ]
    assert Message.role_reads <= 10


def test_non_integer_findings_window_is_rejected():
    manager = ChatContextManager("invalid-window", [])
    manager.MAX_FINDINGS_TO_INCLUDE = 1.5
    with pytest.raises(TypeError):
        manager._extract_findings_from_history()