From 6865ac0272ff0196a71057b9a23dbd4c3f0fe38a Mon Sep 17 00:00:00 2001
From: arsam <me@asabbagh.com>
Date: Fri, 18 Sep 2026 23:06:49 +0330
Subject: [PATCH] Import tests: tests/test_reranker

Import the existing local project snapshot. This commit organizes existing files; it does not represent newly developed functionality.
---
 tests/test_reranker.py | 74 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 74 insertions(+)
 create mode 100644 tests/test_reranker.py

diff --git a/tests/test_reranker.py b/tests/test_reranker.py
new file mode 100644
index 0000000..986474b
--- /dev/null
+++ b/tests/test_reranker.py
@@ -0,0 +1,74 @@
+import pytest
+
+
+def test_chunk_text_single_short_text():
+    from axon.services.reranker import chunk_text
+    chunks = chunk_text("hello world", max_tokens=512)
+    assert chunks == ["hello world"]
+
+
+def test_chunk_text_splits_long_text():
+    from axon.services.reranker import chunk_text
+    # 384 words per chunk at max_tokens=512 (512 * 0.75)
+    text = " ".join([f"word{i}" for i in range(500)])
+    chunks = chunk_text(text, max_tokens=512)
+    assert len(chunks) == 2
+    assert chunks[0].startswith("word0")
+
+
+def test_chunk_text_empty_string():
+    from axon.services.reranker import chunk_text
+    chunks = chunk_text("", max_tokens=512)
+    assert chunks == [""]
+
+
+def test_chunk_text_exact_boundary():
+    from axon.services.reranker import chunk_text
+    # 384 words should be exactly 1 chunk
+    text = " ".join(["x"] * 384)
+    chunks = chunk_text(text, max_tokens=512)
+    assert len(chunks) == 1
+
+
+@pytest.mark.asyncio
+async def test_rerank_results_sorts_by_score(monkeypatch):
+    import numpy as np
+
+    call_count = [0]
+
+    class FakeModel:
+        def predict(self, pairs):
+            # First pair gets low score, second gets high score
+            return np.array([0.1, 0.9])
+
+    monkeypatch.setattr("axon.services.reranker._model", FakeModel())
+
+    from axon.services.reranker import rerank_results
+    contents = [("https://low.com", "low relevance text"), ("https://high.com", "high relevance text")]
+    ranked = await rerank_results("query", contents)
+    assert ranked[0][0] == "https://high.com"
+    assert ranked[1][0] == "https://low.com"
+    assert ranked[0][2] > ranked[1][2]
+
+
+@pytest.mark.asyncio
+async def test_rerank_results_empty_input():
+    from axon.services.reranker import rerank_results
+    result = await rerank_results("query", [])
+    assert result == []
+
+
+@pytest.mark.asyncio
+async def test_rerank_results_handles_empty_content(monkeypatch):
+    import numpy as np
+
+    class FakeModel:
+        def predict(self, pairs):
+            return np.array([0.5] * len(pairs))
+
+    monkeypatch.setattr("axon.services.reranker._model", FakeModel())
+
+    from axon.services.reranker import rerank_results
+    contents = [("https://a.com", ""), ("https://b.com", "some text")]
+    ranked = await rerank_results("query", contents)
+    assert len(ranked) == 2