test: perplexity quality gate tests (#63)

tests/test_quality_gate.py

@@ -0,0 +1,117 @@
+#!/usr/bin/env python3
+"""Tests for benchmarks/quality_gate.py — Perplexity Quality Gate (#63)."""
+
+import json
+import os
+import sys
+import tempfile
+import textwrap
+from pathlib import Path
+from unittest.mock import patch, MagicMock
+
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "benchmarks"))
+from quality_gate import (
+    PerplexityResult,
+    QualityGateResult,
+    measure_perplexity_ollama_proxy,
+    run_quality_gate,
+)
+
+
+class TestPerplexityResult:
+    def test_to_dict(self):
+        r = PerplexityResult(
+            backend="llama-server", kv_type="f16",
+            perplexity=12.5, is_proxy=False, tokens=1000,
+            elapsed_seconds=10.0, method="llama-perplexity", exit_code=0,
+        )
+        d = r.to_dict()
+        assert d["backend"] == "llama-server"
+        assert d["perplexity"] == 12.5
+        assert d["is_proxy"] is False
+
+    def test_proxy_flag(self):
+        r = PerplexityResult(
+            backend="ollama-proxy", kv_type="f16",
+            perplexity=3.2, is_proxy=True, method="proxy heuristic",
+        )
+        assert r.is_proxy is True
+
+
+class TestQualityGateResult:
+    def test_pass(self):
+        f16 = PerplexityResult("llama-server", "f16", 10.0, False)
+        turbo4 = PerplexityResult("llama-server", "turbo4", 10.3, False)
+        gate = QualityGateResult(f16=f16, turbo4=turbo4, delta=0.3, threshold=0.5, passed=True, is_proxy=False)
+        assert gate.passed is True
+        assert gate.delta == 0.3
+
+    def test_fail(self):
+        f16 = PerplexityResult("llama-server", "f16", 10.0, False)
+        turbo4 = PerplexityResult("llama-server", "turbo4", 11.0, False)
+        gate = QualityGateResult(f16=f16, turbo4=turbo4, delta=1.0, threshold=0.5, passed=False, is_proxy=False)
+        assert gate.passed is False
+
+    def test_proxy_warning(self):
+        f16 = PerplexityResult("ollama-proxy", "f16", 5.0, True)
+        gate = QualityGateResult(f16=f16, turbo4=None, delta=None, threshold=0.5, passed=False, is_proxy=True, warning="Only F16 measured")
+        assert gate.is_proxy is True
+        summary = gate.summary()
+        assert "PROXY" in summary or "Proxy" in summary
+
+    def test_to_dict(self):
+        f16 = PerplexityResult("llama-server", "f16", 10.0, False)
+        gate = QualityGateResult(f16=f16, turbo4=None, delta=None, threshold=0.5, passed=False, is_proxy=False)
+        d = gate.to_dict()
+        assert d["f16"]["perplexity"] == 10.0
+        assert d["turbo4"] is None
+        assert d["delta"] is None
+
+    def test_summary_format(self):
+        f16 = PerplexityResult("llama-server", "f16", 10.0, False)
+        turbo4 = PerplexityResult("llama-server", "turbo4", 10.2, False)
+        gate = QualityGateResult(f16=f16, turbo4=turbo4, delta=0.2, threshold=0.5, passed=True, is_proxy=False)
+        summary = gate.summary()
+        assert "F16" in summary
+        assert "Turbo4" in summary
+        assert "PASS" in summary
+        assert "0.2000" in summary
+
+
+class TestOllamaProxy:
+    def test_with_corpus_file(self):
+        with tempfile.NamedTemporaryFile(mode="w", suffix=".txt", delete=False) as f:
+            f.write("The quick brown fox jumps over the lazy dog.\n" * 100)
+            f.flush()
+            result = measure_perplexity_ollama_proxy("test-model", f.name)
+        os.unlink(f.name)
+        # Result should be proxy
+        assert result.is_proxy is True
+        assert result.backend == "ollama-proxy"
+
+    def test_with_missing_corpus(self):
+        result = measure_perplexity_ollama_proxy("test-model", "/nonexistent/corpus.txt")
+        assert result.is_proxy is True
+
+
+class TestRunQualityGate:
+    def test_unknown_backend(self):
+        result = run_quality_gate(backend="unknown", model="test")
+        assert result.passed is False
+        assert "Unknown backend" in result.warning
+
+    def test_llama_server_missing_binary(self):
+        result = run_quality_gate(
+            backend="llama-server",
+            model="test.gguf",
+            corpus="/tmp/nonexistent_corpus.txt",
+            llama_bin="/nonexistent/llama-perplexity",
+        )
+        assert result.f16 is not None
+        assert result.f16.error is not None
+        assert "not found" in result.f16.error.lower()
+
+
+if __name__ == "__main__":
+    import unittest
+    unittest.main()