support virtual packages on generic git hosts (Gitea)

src/apm_cli/deps/github_downloader.py

@@ -1211,22 +1211,46 @@ def _download_github_file(self, dep_ref: DependencyReference, file_path: str, re
             # All raw attempts failed — fall through to API path which
             # handles private repos, rate-limit messaging, and SAML errors.
 
+        # Try raw URL for generic hosts (Gitea, GitLab, etc.)
+        if host.lower() not in ("github.com",) and not host.lower().endswith(".ghe.com"):
+            raw_url = f"https://{host}/{owner}/{repo}/raw/{ref}/{file_path}"
+            raw_headers = {}
+            if token:
+                raw_headers['Authorization'] = f'token {token}'
+            try:
+                response = self._resilient_get(raw_url, headers=raw_headers, timeout=30)
+                if response.status_code == 200:
+                    if verbose_callback:
+                        verbose_callback(f"Downloaded file: {host}/{dep_ref.repo_url}/{file_path}")
+                    return response.content
+            except (requests.RequestException, OSError):
+                pass
+
         # --- Contents API path (authenticated, enterprise, or raw fallback) ---
-        # Build GitHub API URL - format differs by host type
+        # Build API URL candidates - format differs by host type
         if host == "github.com":
-            api_url = f"https://api.github.com/repos/{owner}/{repo}/contents/{file_path}?ref={ref}"
+            api_url_candidates = [
+                f"https://api.github.com/repos/{owner}/{repo}/contents/{file_path}?ref={ref}"
+            ]
         elif host.lower().endswith(".ghe.com"):
-            api_url = f"https://api.{host}/repos/{owner}/{repo}/contents/{file_path}?ref={ref}"
+            api_url_candidates = [
+                f"https://api.{host}/repos/{owner}/{repo}/contents/{file_path}?ref={ref}"
+            ]
         else:
-            api_url = f"https://{host}/api/v3/repos/{owner}/{repo}/contents/{file_path}?ref={ref}"
-
+            # Generic host: negotiate Gitea/Gogs-style contents API versions.
+            api_url_candidates = [
+                f"https://{host}/api/v1/repos/{owner}/{repo}/contents/{file_path}?ref={ref}",
+                f"https://{host}/api/v3/repos/{owner}/{repo}/contents/{file_path}?ref={ref}",
+            ]
+        api_url = api_url_candidates[0]
+
         # Set up authentication headers
         headers = {
             'Accept': 'application/vnd.github.v3.raw'  # Returns raw content directly
         }
         if token:
             headers['Authorization'] = f'token {token}'
-        
+
         # Try to download with the specified ref
         try:
             response = self._resilient_get(api_url, headers=headers, timeout=30)
@@ -1236,33 +1260,59 @@ def _download_github_file(self, dep_ref: DependencyReference, file_path: str, re
             return response.content
         except requests.exceptions.HTTPError as e:
             if e.response.status_code == 404:
-                # Try fallback branches if the specified ref fails
+                # For generic hosts, try remaining API version candidates before ref fallback
+                for candidate_url in api_url_candidates[1:]:
+                    try:
+                        candidate_resp = self._resilient_get(candidate_url, headers=headers, timeout=30)
+                        candidate_resp.raise_for_status()
+                        if verbose_callback:
+                            verbose_callback(f"Downloaded file: {host}/{dep_ref.repo_url}/{file_path}")
+                        return candidate_resp.content
+                    except requests.exceptions.HTTPError as ce:
+                        if ce.response.status_code != 404:
+                            raise RuntimeError(
+                                f"Failed to download {file_path}: HTTP {ce.response.status_code}"
+                            )
+                        # 404 on this version too -- try next
+
+                # All API versions returned 404 -- try fallback ref
                 if ref not in ["main", "master"]:
                     # If original ref failed, don't try fallbacks - it might be a specific version
                     raise RuntimeError(f"File not found: {file_path} at ref '{ref}' in {dep_ref.repo_url}")
-                
+
                 # Try the other default branch
                 fallback_ref = "master" if ref == "main" else "main"
-                
-                # Build fallback API URL
+
+                # Build fallback URL candidates
                 if host == "github.com":
-                    fallback_url = f"https://api.github.com/repos/{owner}/{repo}/contents/{file_path}?ref={fallback_ref}"
+                    fallback_url_candidates = [
+                        f"https://api.github.com/repos/{owner}/{repo}/contents/{file_path}?ref={fallback_ref}"
+                    ]
                 elif host.lower().endswith(".ghe.com"):
-                    fallback_url = f"https://api.{host}/repos/{owner}/{repo}/contents/{file_path}?ref={fallback_ref}"
+                    fallback_url_candidates = [
+                        f"https://api.{host}/repos/{owner}/{repo}/contents/{file_path}?ref={fallback_ref}"
+                    ]
                 else:
-                    fallback_url = f"https://{host}/api/v3/repos/{owner}/{repo}/contents/{file_path}?ref={fallback_ref}"
-
-                try:
-                    response = self._resilient_get(fallback_url, headers=headers, timeout=30)
-                    response.raise_for_status()
-                    if verbose_callback:
-                        verbose_callback(f"Downloaded file: {host}/{dep_ref.repo_url}/{file_path}")
-                    return response.content
-                except requests.exceptions.HTTPError:
-                    raise RuntimeError(
-                        f"File not found: {file_path} in {dep_ref.repo_url} "
-                        f"(tried refs: {ref}, {fallback_ref})"
-                    )
+                    fallback_url_candidates = [
+                        f"https://{host}/api/v1/repos/{owner}/{repo}/contents/{file_path}?ref={fallback_ref}",
+                        f"https://{host}/api/v3/repos/{owner}/{repo}/contents/{file_path}?ref={fallback_ref}",
+                        f"https://{host}/api/v4/repos/{owner}/{repo}/contents/{file_path}?ref={fallback_ref}",
+                    ]
+
+                for fallback_url in fallback_url_candidates:
+                    try:
+                        response = self._resilient_get(fallback_url, headers=headers, timeout=30)
+                        response.raise_for_status()
+                        if verbose_callback:
+                            verbose_callback(f"Downloaded file: {host}/{dep_ref.repo_url}/{file_path}")
+                        return response.content
+                    except requests.exceptions.HTTPError:
+                        pass  # Try next version or ref
+
+                raise RuntimeError(
+                    f"File not found: {file_path} in {dep_ref.repo_url} "
+                    f"(tried refs: {ref}, {fallback_ref})"
+                )
             elif e.response.status_code == 401 or e.response.status_code == 403:
                 # Distinguish rate limiting from auth failure.
                 # GitHub returns 403 with X-RateLimit-Remaining: 0 when the

src/apm_cli/models/dependency/reference.py

@@ -11,6 +11,7 @@
     is_artifactory_path,
     is_azure_devops_hostname,
     is_github_hostname,
+    is_gitlab_hostname,
     is_supported_git_host,
     parse_artifactory_path,
     unsupported_host_error,
@@ -580,10 +581,18 @@ def _detect_virtual_package(cls, dependency_str: str):
                 for seg in path_segments
             )
             has_collection = "collections" in path_segments
+            # GitLab supports nested groups (group/subgroup/repo), so the full
+            # path is the repo -- no shorthand subdirectory splitting.
+            # Use https://gitlab.com/group/subgroup/repo.git for GitLab nested
+            # groups; shorthand subdirectory syntax is not supported for GitLab.
+            # All other generic hosts (Gitea, Bitbucket, self-hosted, etc.) use
+            # the owner/repo convention, so extra segments are a virtual subdir.
             if has_virtual_ext or has_collection:
                 min_base_segments = 2
-            else:
+            elif is_gitlab_hostname(validated_host):
                 min_base_segments = len(path_segments)
+            else:
+                min_base_segments = 2
         else:
             min_base_segments = 2
 
@@ -734,7 +743,7 @@ def _parse_standard_url(
                         user_repo = "/".join(parts[1:])
                 else:
                     user_repo = "/".join(parts[1:3])
-            elif len(parts) >= 2 and "." not in parts[0]:
+            elif len(parts) >= 2 and ("." not in parts[0] or validated_host is not None):
                 if not host:
                     host = default_host()
                 if is_azure_devops_hostname(host) and len(parts) >= 3:

src/apm_cli/utils/github_host.py

@@ -29,6 +29,23 @@ def is_azure_devops_hostname(hostname: Optional[str]) -> bool:
     return False
 
 
+def is_gitlab_hostname(hostname: Optional[str]) -> bool:
+    """Return True if hostname is GitLab (cloud or self-hosted).
+
+    GitLab supports nested groups (group/subgroup/repo), so paths with
+    more than two segments should be treated as repo paths, not virtual
+    subdirectory packages.
+
+    Accepts:
+    - gitlab.com
+    - Any hostname starting with 'gitlab.' (common self-hosted convention)
+    """
+    if not hostname:
+        return False
+    h = hostname.lower()
+    return h == "gitlab.com" or h.startswith("gitlab.")
+
+
 def is_github_hostname(hostname: Optional[str]) -> bool:
     """Return True if hostname should be treated as GitHub (cloud or enterprise).
 

tests/test_github_downloader.py

@@ -1629,5 +1629,147 @@ def test_try_raw_download_returns_content_on_200(self):
             assert result == b'hello world'
 
 
+# ---------------------------------------------------------------------------
+# Generic host (Gitea / GitLab) download tests
+# ---------------------------------------------------------------------------
+
+def _make_resp(status_code: int, content: bytes = b"") -> Mock:
+    """Build a minimal mock requests.Response."""
+    resp = Mock()
+    resp.status_code = status_code
+    resp.content = content
+    if status_code >= 400:
+        resp.raise_for_status = Mock(
+            side_effect=requests_lib.exceptions.HTTPError(response=resp)
+        )
+    else:
+        resp.raise_for_status = Mock()
+    return resp
+
+
+class TestGiteaRawUrlDownload:
+    """Gitea raw URL path: /{owner}/{repo}/raw/{ref}/{file}."""
+
+    def setup_method(self):
+        with patch.dict(os.environ, {}, clear=True), _CRED_FILL_PATCH:
+            self.downloader = GitHubPackageDownloader()
+
+    def test_raw_url_succeeds_on_first_attempt(self):
+        """Raw URL returns 200 -- content returned without calling the API."""
+        dep_ref = DependencyReference.parse("gitea.myorg.com/owner/repo")
+        expected = b"# README content"
+        raw_ok = _make_resp(200, expected)
+
+        with patch.object(self.downloader, "_resilient_get", return_value=raw_ok) as mock_get:
+            result = self.downloader.download_raw_file(dep_ref, "README.md", "main")
+
+        assert result == expected
+        first_url = mock_get.call_args_list[0][0][0]
+        assert first_url == "https://gitea.myorg.com/owner/repo/raw/main/README.md"
+        assert mock_get.call_count == 1
+
+    def test_raw_url_with_token_adds_auth_header(self):
+        """Token is forwarded as Authorization header in the raw URL request.
+
+        Token resolution is lazy, so the env patch must stay active for the
+        duration of the download call.
+        """
+        dep_ref = DependencyReference.parse("gitea.myorg.com/owner/repo")
+        raw_ok = _make_resp(200, b"data")
+
+        with patch.dict(os.environ, {"GITHUB_APM_PAT": "gta-tok"}, clear=True):
+            with _CRED_FILL_PATCH:
+                downloader = GitHubPackageDownloader()
+            with patch.object(downloader, "_resilient_get", return_value=raw_ok) as mock_get:
+                downloader.download_raw_file(dep_ref, "README.md", "main")
+
+        raw_headers = mock_get.call_args_list[0][1].get("headers", {})
+        assert "Authorization" in raw_headers
+
+    def test_falls_back_to_api_v1_when_raw_returns_non_200(self):
+        """When the raw URL returns 404, the API v1 path is tried next."""
+        dep_ref = DependencyReference.parse("gitea.myorg.com/owner/repo")
+        expected = b"file via API"
+
+        with patch.object(
+            self.downloader, "_resilient_get",
+            side_effect=[_make_resp(404), _make_resp(200, expected)]
+        ) as mock_get:
+            result = self.downloader.download_raw_file(dep_ref, "README.md", "main")
+
+        assert result == expected
+        urls = [c[0][0] for c in mock_get.call_args_list]
+        assert urls[0] == "https://gitea.myorg.com/owner/repo/raw/main/README.md"
+        assert "/api/v1/" in urls[1]
+
+
+class TestGitLabApiVersionNegotiation:
+    """API version negotiation: v1 -> v3 -> v4 for generic hosts."""
+
+    def setup_method(self):
+        with patch.dict(os.environ, {}, clear=True), _CRED_FILL_PATCH:
+            self.downloader = GitHubPackageDownloader()
+
+    def test_gitlab_v4_reached_after_v1_and_v3_return_404(self):
+        """GitLab uses /api/v4/ -- negotiation must try v1, v3, then v4."""
+        dep_ref = DependencyReference.parse("gitlab.myorg.com/owner/repo")
+        expected = b"gitlab file content"
+
+        side_effects = [
+            _make_resp(404),           # raw URL
+            _make_resp(404),           # v1
+            _make_resp(404),           # v3
+            _make_resp(200, expected), # v4
+        ]
+        with patch.object(self.downloader, "_resilient_get", side_effect=side_effects) as mock_get:
+            result = self.downloader.download_raw_file(dep_ref, "skill.md", "main")
+
+        assert result == expected
+        urls = [c[0][0] for c in mock_get.call_args_list]
+        assert "/api/v1/" in urls[1]
+        assert "/api/v3/" in urls[2]
+        assert "/api/v4/" in urls[3]
+
+    def test_gitea_v1_succeeds_without_trying_v3_or_v4(self):
+        """When v1 returns 200, v3 and v4 must never be called."""
+        dep_ref = DependencyReference.parse("gitea.example.com/owner/repo")
+        expected = b"gitea content"
+
+        with patch.object(
+            self.downloader, "_resilient_get",
+            side_effect=[_make_resp(404), _make_resp(200, expected)]
+        ) as mock_get:
+            result = self.downloader.download_raw_file(dep_ref, "file.md", "main")
+
+        assert result == expected
+        urls = [c[0][0] for c in mock_get.call_args_list]
+        assert all("/api/v3/" not in u and "/api/v4/" not in u for u in urls)
+
+    def test_all_api_versions_404_raises_runtime_error(self):
+        """When every API version returns 404 for both refs, a clear error is raised."""
+        dep_ref = DependencyReference.parse("git.example.com/owner/repo")
+        # raw + v1 + v3 + v4 for 'main', then v1 + v3 + v4 for 'master' fallback
+        side_effects = [_make_resp(404)] * 8
+
+        with patch.object(self.downloader, "_resilient_get", side_effect=side_effects):
+            with pytest.raises(RuntimeError, match="File not found"):
+                self.downloader.download_raw_file(dep_ref, "missing.md", "main")
+
+    def test_github_com_uses_api_github_com_not_api_v4(self):
+        """github.com must still use api.github.com, never /api/v4/."""
+        dep_ref = DependencyReference.parse("owner/repo")
+        expected = b"github content"
+        api_ok = _make_resp(200, expected)
+
+        with patch.object(self.downloader, "_try_raw_download", return_value=None):
+            with patch.object(self.downloader, "_resilient_get", return_value=api_ok) as mock_get:
+                result = self.downloader.download_raw_file(dep_ref, "README.md", "main")
+
+        assert result == expected
+        url_called = mock_get.call_args_list[0][0][0]
+        assert url_called.startswith("https://api.github.com/")
+        assert "/api/v4/" not in url_called
+
+
 if __name__ == '__main__':
     pytest.main([__file__])