fix: unified scraper temp config uses unified format for doc_scraper (#317)

The unified scraper's _scrape_documentation() was creating temp configs
in flat/legacy format (no "sources" key), causing doc_scraper's
ConfigValidator to reject them. Wrap the temp config in unified format
with a "sources" array. Also remove dead code branches and fix a
pre-existing test that didn't clear GITHUB_TOKEN from env.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

tests/test_github_scraper.py

@@ -68,7 +68,12 @@ class TestGitHubScraperInitialization(unittest.TestCase):
             "github_token": "test_token_123",
         }
 
-        with patch("skill_seekers.cli.github_scraper.Github") as mock_github:
+        # Clear GITHUB_TOKEN env var so config token is used (env takes priority)
+        env = {k: v for k, v in os.environ.items() if k != "GITHUB_TOKEN"}
+        with (
+            patch.dict(os.environ, env, clear=True),
+            patch("skill_seekers.cli.github_scraper.Github") as mock_github,
+        ):
             _scraper = self.GitHubScraper(config)
             mock_github.assert_called_once_with("test_token_123")
 

tests/test_unified_scraper_orchestration.py

@@ -224,7 +224,11 @@ class TestScrapeDocumentation:
             mock_run.return_value = MagicMock(returncode=1, stdout="", stderr="")
             scraper._scrape_documentation(source)
 
-        assert any("llms_txt_url" in c for c in written_configs)
+        assert any(
+            "llms_txt_url" in s
+            for c in written_configs
+            for s in c.get("sources", [c])
+        )
 
     def test_start_urls_forwarded_to_doc_config(self, tmp_path):
         """start_urls from source is forwarded to the temporary doc config."""
@@ -247,7 +251,11 @@ class TestScrapeDocumentation:
             mock_run.return_value = MagicMock(returncode=1, stdout="", stderr="")
             scraper._scrape_documentation(source)
 
-        assert any("start_urls" in c for c in written_configs)
+        assert any(
+            "start_urls" in s
+            for c in written_configs
+            for s in c.get("sources", [c])
+        )
 
 
 # ===========================================================================