More bugfixes in the glossary protection guard module

tests/test_prompts.py

@@ -70,6 +70,44 @@ def test_prompt_uses_simplified_segment_payload():
     assert "end" not in prompt_segments[0]
 
 
+def test_prompts_do_not_include_inferred_plurals():
+    transcript = parse_transcript_json(
+        """
+        [
+          {"id": 1, "speaker": "Eric", "start": 0.0, "end": 1.0, "text": "The gestures are nearby."}
+        ]
+        """
+    )
+    glossary = parse_glossary_yaml(
+        """
+        glossary:
+          - name: "Godfrey"
+            aliases:
+              - "Jester"
+            category: npc
+            summary: "Godfrey is an NPC."
+        """
+    )
+    section = chunk_transcript(transcript, max_section_tokens=16000)[0]
+
+    glossary_messages = build_glossary_correction_messages(section, glossary)
+    glossary_json = glossary_messages[1]["content"].split("Glossary:\n", maxsplit=1)[1].split(
+        "\n\nTranscript section:",
+        maxsplit=1,
+    )[0]
+    grammar_messages = build_grammar_correction_messages(section, glossary)
+    grammar_json = grammar_messages[1]["content"].split("Protected glossary/context:\n", maxsplit=1)[1].split(
+        "\n\nTranscript section:",
+        maxsplit=1,
+    )[0]
+
+    for prompt_glossary in (json.loads(glossary_json), json.loads(grammar_json)):
+        entry = prompt_glossary["glossary"][0]
+        assert "plural" not in entry
+        assert "Godfreys" not in json.dumps(prompt_glossary)
+        assert "Jesters" not in json.dumps(prompt_glossary)
+
+
 def test_grammar_prompt_limits_readability_corrections_and_protects_glossary():
     transcript = parse_transcript_json(
         """