feat: improve unit tests quality and coverage

tests/test_flow_integration.py

@@ -49,8 +49,8 @@ async def test_remote_repository_analysis(request: pytest.FixtureRequest) -> Non
     """Test the complete flow of analyzing a remote repository."""
     client = request.getfixturevalue("test_client")
     form_data = {
-        "input_text": "https://github.com/octocat/Hello-World",
-        "max_file_size": "243",
+        "input_text": "https://github.com/pallets/flask",
+        "max_file_size": "200",
         "pattern_type": "exclude",
         "pattern": "",
         "token": "",
@@ -75,7 +75,7 @@ async def test_invalid_repository_url(request: pytest.FixtureRequest) -> None:
     client = request.getfixturevalue("test_client")
     form_data = {
         "input_text": "https://github.com/nonexistent/repo",
-        "max_file_size": "243",
+        "max_file_size": "200",
         "pattern_type": "exclude",
         "pattern": "",
         "token": "",
@@ -92,12 +92,11 @@ async def test_invalid_repository_url(request: pytest.FixtureRequest) -> None:
 
 @pytest.mark.asyncio
 async def test_large_repository(request: pytest.FixtureRequest) -> None:
-    """Simulate analysis of a large repository with nested folders."""
+    """Simulate analysis of a large repository with nested folders and many files."""
     client = request.getfixturevalue("test_client")
-    # TODO: ingesting a large repo take too much time (eg: godotengine/godot repository)
     form_data = {
-        "input_text": "https://github.com/octocat/hello-world",
-        "max_file_size": "10",
+        "input_text": "https://github.com/pallets/flask",
+        "max_file_size": "100",  # Lower this to force skipping large files
         "pattern_type": "exclude",
         "pattern": "",
         "token": "",
@@ -109,7 +108,7 @@ async def test_large_repository(request: pytest.FixtureRequest) -> None:
     response_data = response.json()
     if response.status_code == status.HTTP_200_OK:
         assert "content" in response_data
-        assert response_data["content"]
+        assert isinstance(response_data["content"], str)
     else:
         assert "error" in response_data
 
@@ -121,8 +120,8 @@ async def test_concurrent_requests(request: pytest.FixtureRequest) -> None:
 
     def make_request() -> None:
         form_data = {
-            "input_text": "https://github.com/octocat/hello-world",
-            "max_file_size": "243",
+            "input_text": "https://github.com/pallets/flask",
+            "max_file_size": "200",
             "pattern_type": "exclude",
             "pattern": "",
             "token": "",
@@ -148,7 +147,7 @@ async def test_large_file_handling(request: pytest.FixtureRequest) -> None:
     """Test handling of repositories with large files."""
     client = request.getfixturevalue("test_client")
     form_data = {
-        "input_text": "https://github.com/octocat/Hello-World",
+        "input_text": "https://github.com/pallets/flask",
         "max_file_size": "1",
         "pattern_type": "exclude",
         "pattern": "",
@@ -171,8 +170,8 @@ async def test_repository_with_patterns(request: pytest.FixtureRequest) -> None:
     """Test repository analysis with include/exclude patterns."""
     client = request.getfixturevalue("test_client")
     form_data = {
-        "input_text": "https://github.com/octocat/Hello-World",
-        "max_file_size": "243",
+        "input_text": "https://github.com/pallets/flask",
+        "max_file_size": "200",
         "pattern_type": "include",
         "pattern": "*.md",
         "token": "",
@@ -184,9 +183,120 @@ async def test_repository_with_patterns(request: pytest.FixtureRequest) -> None:
     response_data = response.json()
     if response.status_code == status.HTTP_200_OK:
         assert "content" in response_data
+        assert isinstance(response_data["content"], str)
+
+        assert "repo_url" in response_data
+        assert response_data["repo_url"].startswith("https://github.com/")
+
+        assert "summary" in response_data
+        assert isinstance(response_data["summary"], str)
+        assert "pallets/flask" in response_data["summary"].lower()
+
+        assert "tree" in response_data
+        assert isinstance(response_data["tree"], str)
+        assert "pallets-flask" in response_data["tree"].lower()
+
         assert "pattern_type" in response_data
         assert response_data["pattern_type"] == "include"
+
         assert "pattern" in response_data
         assert response_data["pattern"] == "*.md"
     else:
         assert "error" in response_data
+        assert isinstance(response_data["error"], str)
+        assert response_data["error"]
+
+
+@pytest.mark.asyncio
+async def test_missing_required_fields(request: pytest.FixtureRequest) -> None:
+    """Test API response when required fields are missing."""
+    client = request.getfixturevalue("test_client")
+    form_data = {
+        "max_file_size": "200",
+        "pattern_type": "exclude",
+        "pattern": "",
+        "token": "",
+    }
+    response = client.post("/api/ingest", json=form_data)
+    assert response.status_code in (
+        status.HTTP_422_UNPROCESSABLE_ENTITY,
+        status.HTTP_429_TOO_MANY_REQUESTS,
+    )
+
+    form_data = {
+        "input_text": "https://github.com/pallets/flask",
+        "max_file_size": "200",
+        "pattern": "",
+        "token": "",
+    }
+    response = client.post("/api/ingest", json=form_data)
+    assert response.status_code in (
+        status.HTTP_422_UNPROCESSABLE_ENTITY,
+        status.HTTP_429_TOO_MANY_REQUESTS,
+        status.HTTP_200_OK,
+    )
+
+
+@pytest.mark.asyncio
+async def test_invalid_field_types(request: pytest.FixtureRequest) -> None:
+    """Test API response when fields have invalid types."""
+    client = request.getfixturevalue("test_client")
+
+    form_data = {
+        "input_text": 12345,
+        "max_file_size": "200",
+        "pattern_type": "exclude",
+        "pattern": "",
+        "token": "",
+    }
+    response = client.post("/api/ingest", json=form_data)
+    assert response.status_code == status.HTTP_422_UNPROCESSABLE_ENTITY
+
+    form_data = {
+        "input_text": "https://github.com/pallets/flask",
+        "max_file_size": "200",
+        "pattern_type": "exclude",
+        "pattern": ["*.md"],
+        "token": "",
+    }
+    response = client.post("/api/ingest", json=form_data)
+    assert response.status_code == status.HTTP_422_UNPROCESSABLE_ENTITY
+
+
+@pytest.mark.asyncio
+async def test_unsupported_pattern_type(request: pytest.FixtureRequest) -> None:
+    """Test API response for unsupported pattern_type."""
+    client = request.getfixturevalue("test_client")
+    form_data = {
+        "input_text": "https://github.com/pallets/flask",
+        "max_file_size": "200",
+        "pattern_type": "invalid_type",
+        "pattern": "*.md",
+        "token": "",
+    }
+    response = client.post("/api/ingest", json=form_data)
+    assert response.status_code in (status.HTTP_400_BAD_REQUEST, status.HTTP_422_UNPROCESSABLE_ENTITY)
+    response_data = response.json()
+    assert "error" in response_data or "detail" in response_data
+
+
+@pytest.mark.asyncio
+async def test_invalid_token(request: pytest.FixtureRequest) -> None:
+    """Test API response for an invalid or expired token."""
+    client = request.getfixturevalue("test_client")
+    form_data = {
+        "input_text": "https://github.com/pallets/flask",
+        "max_file_size": "200",
+        "pattern_type": "exclude",
+        "pattern": "",
+        "token": "invalid_token_1234567890",
+    }
+    response = client.post("/api/ingest", json=form_data)
+    # Accept all likely error codes for invalid token
+    assert response.status_code in (
+        status.HTTP_401_UNAUTHORIZED,
+        status.HTTP_400_BAD_REQUEST,
+        status.HTTP_429_TOO_MANY_REQUESTS,
+    ), f"Unexpected status code: {response.status_code}"
+    response_data = response.json()
+    assert "error" in response_data or "detail" in response_data

tests/test_git_utils.py

@@ -277,3 +277,30 @@ def test_create_git_command_ignores_non_github_urls(
     # Should only have base command and -C option, no auth headers
     expected = [*base_cmd, "-C", local_path]
     assert cmd == expected
+
+
+@pytest.mark.parametrize(
+    "url",
+    [
+        "",
+        "not-a-url",
+        "ftp://github.com/owner/repo.git",
+        "github.com/owner/repo.git",
+        "https://",
+    ],
+)
+def test_is_github_host_edge_cases(url: str) -> None:
+    """Test is_github_host with malformed or edge-case URLs."""
+    try:
+        result = is_github_host(url)
+        assert isinstance(result, bool)
+    except (ValueError, TypeError) as exc:
+        pytest.fail(f"is_github_host raised {exc.__class__.__name__} for url: {url}")
+
+
+def test_token_not_in_command_plaintext() -> None:
+    """Ensure the token is not present in the command as plain text."""
+    token = "ghp_" + "x" * 36
+    cmd = create_git_command(["git", "clone"], "/tmp", "https://github.com/owner/repo.git", token)
+    for part in cmd:
+        assert token not in part or "Basic" in part