Initial MVP

tests/test_config.py

@@ -0,0 +1,131 @@
+"""Tests for configuration loading, merging, and ENV overrides."""
+
+import os
+from pathlib import Path
+
+import pytest
+import yaml
+
+from kb_search.config import (
+    DEFAULTS,
+    _deep_merge,
+    _get_nested,
+    _set_nested,
+    config_with_sources,
+    load_config,
+    save_config_value,
+)
+
+
+def test_deep_merge_basic():
+    base = {"a": 1, "b": {"c": 2, "d": 3}}
+    override = {"b": {"c": 99}}
+    result = _deep_merge(base, override)
+    assert result == {"a": 1, "b": {"c": 99, "d": 3}}
+
+
+def test_deep_merge_new_keys():
+    base = {"a": 1}
+    override = {"b": 2}
+    result = _deep_merge(base, override)
+    assert result == {"a": 1, "b": 2}
+
+
+def test_deep_merge_does_not_mutate():
+    base = {"a": {"b": 1}}
+    override = {"a": {"b": 2}}
+    _deep_merge(base, override)
+    assert base["a"]["b"] == 1
+
+
+def test_set_nested():
+    d = {}
+    _set_nested(d, "a.b.c", 42)
+    assert d == {"a": {"b": {"c": 42}}}
+
+
+def test_get_nested():
+    d = {"a": {"b": {"c": 42}}}
+    assert _get_nested(d, "a.b.c") == 42
+    assert _get_nested(d, "a.b.x", "missing") == "missing"
+    assert _get_nested(d, "x.y.z") is None
+
+
+def test_load_config_defaults(tmp_path):
+    """With no config file, returns defaults."""
+    cfg = load_config(tmp_path / "nonexistent.yaml")
+    assert cfg["embedding"]["model"] == "all-MiniLM-L6-v2"
+    assert cfg["search"]["default_top"] == 10
+    assert cfg["chunking"]["pdf"]["strategy"] == "hierarchy"
+
+
+def test_load_config_yaml_override(tmp_path):
+    """YAML values override defaults."""
+    config_path = tmp_path / "config.yaml"
+    config_path.write_text(yaml.dump({"embedding": {"model": "nomic-embed-text"}}))
+    cfg = load_config(config_path)
+    assert cfg["embedding"]["model"] == "nomic-embed-text"
+    # Other defaults preserved
+    assert cfg["search"]["default_top"] == 10
+
+
+def test_load_config_env_override(tmp_path, monkeypatch):
+    """ENV overrides both YAML and defaults."""
+    config_path = tmp_path / "config.yaml"
+    config_path.write_text(yaml.dump({"search": {"default_top": 20}}))
+    monkeypatch.setenv("KB_DEFAULT_TOP", "50")
+    cfg = load_config(config_path)
+    assert cfg["search"]["default_top"] == 50
+
+
+def test_load_config_env_model(tmp_path, monkeypatch):
+    monkeypatch.setenv("KB_MODEL", "bge-small-en-v1.5")
+    cfg = load_config(tmp_path / "nonexistent.yaml")
+    assert cfg["embedding"]["model"] == "bge-small-en-v1.5"
+
+
+def test_save_config_value(tmp_path):
+    config_path = tmp_path / "config.yaml"
+    save_config_value(config_path, "chunking.pdf.max_tokens", "2048")
+    with open(config_path) as f:
+        data = yaml.safe_load(f)
+    assert data["chunking"]["pdf"]["max_tokens"] == 2048
+
+
+def test_save_config_value_bool(tmp_path):
+    config_path = tmp_path / "config.yaml"
+    save_config_value(config_path, "chunking.code.include_context", "false")
+    with open(config_path) as f:
+        data = yaml.safe_load(f)
+    assert data["chunking"]["code"]["include_context"] is False
+
+
+def test_save_config_preserves_existing(tmp_path):
+    config_path = tmp_path / "config.yaml"
+    config_path.write_text(yaml.dump({"embedding": {"model": "custom"}}))
+    save_config_value(config_path, "search.default_top", "20")
+    with open(config_path) as f:
+        data = yaml.safe_load(f)
+    assert data["embedding"]["model"] == "custom"
+    assert data["search"]["default_top"] == 20
+
+
+def test_config_with_sources_defaults(tmp_path, monkeypatch):
+    entries = config_with_sources(tmp_path / "nonexistent.yaml")
+    sources = {k: s for k, _, s in entries}
+    assert sources["embedding.model"] == "default"
+
+
+def test_config_with_sources_yaml(tmp_path):
+    config_path = tmp_path / "config.yaml"
+    config_path.write_text(yaml.dump({"embedding": {"model": "custom"}}))
+    entries = config_with_sources(config_path)
+    sources = {k: s for k, _, s in entries}
+    assert sources["embedding.model"] == "config.yaml"
+
+
+def test_config_with_sources_env(tmp_path, monkeypatch):
+    monkeypatch.setenv("KB_MODEL", "from-env")
+    entries = config_with_sources(tmp_path / "nonexistent.yaml")
+    sources = {k: s for k, _, s in entries}
+    assert sources["embedding.model"] == "env (KB_MODEL)"