feat: improve unit tests quality and coverage

tests/server/test_flow_integration.py

@@ -1,5 +1,6 @@
 """Integration tests covering core functionalities, edge cases, and concurrency handling."""
 
+import re
 import shutil
 import sys
 from concurrent.futures import ThreadPoolExecutor
@@ -93,9 +94,8 @@ 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,
@@ -110,7 +110,7 @@ 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
 
@@ -169,25 +169,144 @@ async def test_large_file_handling(request: pytest.FixtureRequest) -> None:
 
 @pytest.mark.asyncio
 async def test_repository_with_patterns(request: pytest.FixtureRequest) -> None:
-    """Test repository analysis with include/exclude patterns."""
+    """Test repository analysis using include patterns on a real GitHub repo."""
     client = request.getfixturevalue("test_client")
+
+    # Target repository and file pattern
+    repo_url = "https://github.com/pallets/flask"
+    pattern = "*.md"
+
     form_data = {
-        "input_text": "https://github.com/octocat/Hello-World",
+        "input_text": repo_url,
         "max_file_size": 243,
         "pattern_type": "include",
-        "pattern": "*.md",
+        "pattern": pattern,
         "token": "",
     }
 
     response = client.post("/api/ingest", json=form_data)
-    assert response.status_code == status.HTTP_200_OK, f"Request failed: {response.text}"
+    assert response.status_code == status.HTTP_200_OK, f"Expected 200 OK, got {response.status_code}: {response.text}"
 
     response_data = response.json()
-    if response.status_code == status.HTTP_200_OK:
-        assert "content" in response_data
-        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, dict), "Response is not a JSON object"
+
+    # Ruff-compliant assertions
+    assert "content" in response_data, "Missing 'content' in response"
+    assert isinstance(response_data["content"], str), "'content' is not a string"
+
+    assert "repo_url" in response_data, "Missing 'repo_url'"
+    assert response_data["repo_url"].startswith("https://github.com/"), (
+        "'repo_url' does not start with expected prefix"
+    )
+
+    assert "summary" in response_data, "Missing 'summary'"
+    assert isinstance(response_data["summary"], str), "'summary' is not a string"
+
+    assert "tree" in response_data, "Missing 'tree'"
+    assert isinstance(response_data["tree"], str), "'tree' is not a string"
+
+    assert "pattern_type" in response_data, "Missing 'pattern_type'"
+    assert response_data["pattern_type"] == "include", "Unexpected 'pattern_type' value"
+
+    assert "pattern" in response_data, "Missing 'pattern'"
+    assert response_data["pattern"] == pattern, "Unexpected 'pattern' value"
+
+    # Dynamically validate repo name
+    repo_slug = re.sub(r"https://github\.com/", "", repo_url).lower()
+    assert repo_slug in response_data["summary"].lower(), f"Expected repo slug '{repo_slug}' in summary"
+    assert repo_slug.replace("/", "-") in response_data["tree"].lower(), f"Expected slug '{repo_slug}' in tree"
+
+
+@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