refactor (untested)

tests/test_config.py

@@ -0,0 +1,77 @@
+"""Deeper tests for WorkflowConfig — the --transcript-formats parsing and the
+post-cleanup shape (embed-images only; deprecated analysis attrs gone)."""
+import unittest
+
+from meetus.workflow import WorkflowConfig
+
+
+def cfg(**kw):
+    kw.setdefault("video", "sample.mp4")
+    return WorkflowConfig(**kw)
+
+
+class TestTranscriptFormats(unittest.TestCase):
+    def test_default_is_json_only(self):
+        self.assertEqual(cfg().transcript_formats, ["json"])
+
+    def test_srt_implies_json(self):
+        # User shouldn't have to list json; it's always the base.
+        self.assertEqual(cfg(transcript_formats="srt").transcript_formats,
+                         ["json", "srt"])
+
+    def test_multiple(self):
+        self.assertEqual(cfg(transcript_formats="srt,txt").transcript_formats,
+                         ["json", "srt", "txt"])
+
+    def test_all_expands(self):
+        self.assertEqual(set(cfg(transcript_formats="all").transcript_formats),
+                         {"json", "srt", "vtt", "txt", "tsv"})
+
+    def test_dedup_and_json_kept(self):
+        self.assertEqual(cfg(transcript_formats="json,srt,srt").transcript_formats,
+                         ["json", "srt"])
+
+    def test_whitespace_and_case(self):
+        self.assertEqual(cfg(transcript_formats=" SRT , Txt ").transcript_formats,
+                         ["json", "srt", "txt"])
+
+    def test_invalid_raises(self):
+        with self.assertRaises(ValueError):
+            cfg(transcript_formats="srt,bogus")
+
+
+class TestDefaults(unittest.TestCase):
+    def test_scalar_defaults(self):
+        c = cfg()
+        self.assertEqual(c.embed_quality, 80)
+        self.assertEqual(c.format, "detailed")
+        self.assertEqual(c.whisper_model, "medium")
+        self.assertEqual(c.scene_threshold, 15.0)
+
+    def test_to_dict_analysis_is_embed_images(self):
+        self.assertEqual(cfg().to_dict()["analysis"]["method"], "embed-images")
+
+    def test_to_dict_whisper_has_diarize_and_formats(self):
+        d = cfg(diarize=True, transcript_formats="srt").to_dict()
+        self.assertTrue(d["whisper"]["diarize"])
+        self.assertEqual(d["whisper"]["transcript_formats"], ["json", "srt"])
+
+
+class TestDeprecatedRemoved(unittest.TestCase):
+    """The OCR/vision/hybrid surface was removed in the cleanup."""
+
+    def test_no_deprecated_attrs(self):
+        c = cfg()
+        for attr in ("use_vision", "use_hybrid", "hybrid_llm_cleanup",
+                     "hybrid_llm_model", "vision_model", "vision_context",
+                     "ocr_engine", "no_deduplicate"):
+            self.assertFalse(hasattr(c, attr), f"{attr} should be removed")
+
+    def test_extra_kwargs_are_ignored(self):
+        # Stray kwargs (e.g. an old flag) must not crash construction.
+        c = cfg(use_vision=True, ocr_engine="tesseract")
+        self.assertFalse(hasattr(c, "use_vision"))
+
+
+if __name__ == "__main__":
+    unittest.main()