2125_GCE/LLMCompress/tests/test_llm_compress.py

"""Tests for LLMCompress subsystem.

These tests verify:

- LLMAdapter normalization
- compress_interaction() end-to-end flow
- compress_session() multi-turn flow
- Integration with GlyphOS Cognitive Kernel
- Event emission during compression

This uses a fake LLM backend so tests run without external dependencies.
"""

from typing import Any, Dict

from LLMCompress import (
    LLMAdapter,
    compress_interaction,
    compress_session,
    CompressionReport,
)

from glyphos.events import get_event_bus
from glyphos.cognitive_kernel import get_kernel  # noqa: F401  # imported to ensure availability


# ---------------------------------------------------------------------------
# Fake LLM backend
# ---------------------------------------------------------------------------

def fake_llm_backend(prompt: str, **kwargs: Any) -> Dict[str, Any]:
    """A deterministic fake LLM backend for testing."""
    return {
        "response": f"FAKE_RESPONSE({prompt})",
        "tokens_prompt": len(prompt.split()),
        "tokens_response": 3,
        "model_name": "fake-llm-test",
        "extra_info": "ok",
    }


# ---------------------------------------------------------------------------
# Tests
# ---------------------------------------------------------------------------

def test_adapter_normalization():
    adapter = LLMAdapter(fake_llm_backend, model_name="fake-llm-test")
    out = adapter.run("hello world")

    assert out.prompt == "hello world"
    assert out.response.startswith("FAKE_RESPONSE")
    assert out.tokens_prompt == 2
    assert out.tokens_response == 3
    assert out.model_name == "fake-llm-test"
    assert isinstance(out.metadata, dict)


def test_compress_interaction_basic():
    adapter = LLMAdapter(fake_llm_backend, model_name="fake-llm-test")

    bus = get_event_bus()
    bus.clear_history()

    report = compress_interaction(adapter, "hello test")

    # Report structure
    assert isinstance(report, CompressionReport)
    assert len(report.interactions) == 1
    assert "prompt" in report.interactions[0]
    assert "response" in report.interactions[0]

    # Kernel output
    assert isinstance(report.fused_symbol, dict)
    assert isinstance(report.diagnostics, dict)

    # Events fired
    history = bus.get_history(limit=10)
    types = [e["type"] for e in history]

    assert "cognition.started" in types
    assert "cognition.completed" in types


def test_compress_session_multi_turn():
    adapter = LLMAdapter(fake_llm_backend, model_name="fake-llm-test")

    bus = get_event_bus()
    bus.clear_history()

    prompts = ["turn one", "turn two", "turn three"]
    report = compress_session(adapter, prompts)

    assert isinstance(report, CompressionReport)
    assert len(report.interactions) == 3

    # Kernel output
    assert isinstance(report.fused_symbol, dict)
    assert isinstance(report.diagnostics, dict)

    # Events fired
    history = bus.get_history(limit=10)
    types = [e["type"] for e in history]

    assert "cognition.started" in types
    assert "cognition.completed" in types


def test_payload_encoding_is_valid_json():
    adapter = LLMAdapter(fake_llm_backend)
    report = compress_interaction(adapter, "encode me")

    # Ensure payload was JSON-serializable and processed by kernel
    assert isinstance(report.fused_symbol, dict)
    assert isinstance(report.diagnostics, dict)


def test_event_metadata_includes_source():
    adapter = LLMAdapter(fake_llm_backend)

    bus = get_event_bus()
    bus.clear_history()

    compress_interaction(adapter, "metadata test")

    events = bus.get_history(limit=10)
    found = False
    for e in events:
        if e["type"] == "cognition.started":
            assert e["payload"]["source"] == "LLMCompress"
            found = True
            break

    assert found, "Expected cognition.started event with source=LLMCompress"