Implemented optional concurrency for the LLM backend

tests/test_new_cli.py

@@ -21,6 +21,7 @@ def test_process_help_exposes_framework_flags(capsys):
     output = capsys.readouterr().out
     assert "--report-json" in output
     assert "--llm-api-key" in output
+    assert "--llm-concurrency" in output
     assert "--modules" in output
     assert "--model" in output
     assert "--base-url" in output
@@ -194,3 +195,57 @@ def test_cli_process_passes_llm_api_key_override_to_config(monkeypatch, tmp_path
 
     assert exit_code == 0
     assert captured["llm_api_key"] == "cli-key"
+
+
+def test_cli_process_passes_llm_concurrency_override_to_config(monkeypatch, tmp_path):
+    captured = {}
+    transcript = parse_transcript_json(
+        """
+        [
+          {"id": 1, "speaker": "Eric", "start": 0.0, "end": 1.0, "text": "Fixed."}
+        ]
+        """
+    )
+    report = RunReport(
+        status="success",
+        config={"model": "m", "base_url": "b"},
+        normalization={"source_segment_count": 1, "normalized_segment_count": 1, "merge_count": 0},
+        pipeline=["grammar"],
+        modules=[],
+        applied_changes=[],
+        skipped_corrections=[],
+        totals={"output_segment_count": 1, "applied_change_count": 0, "skipped_correction_count": 0},
+        work_dir_retention="auto",
+        work_dir_retained=False,
+        work_dir=None,
+        error=None,
+    )
+    result = ProcessResult(
+        transcript=transcript,
+        report=report,
+        run_dir=tmp_path / "run",
+        work_dir_retained=False,
+    )
+
+    def _fake_from_sources(*, overrides=None):
+        captured["llm_concurrency"] = overrides.llm_concurrency
+        return object()
+
+    monkeypatch.setattr("audita.cli.AuditaConfig.from_sources", _fake_from_sources)
+    monkeypatch.setattr("audita.cli.load_transcript", lambda path: [])
+    monkeypatch.setattr("audita.cli.load_glossary", lambda path: object())
+    monkeypatch.setattr("audita.cli.process_transcript_result", lambda *args, **kwargs: result)
+
+    exit_code = main(
+        [
+            "process",
+            "transcript.json",
+            "--glossary",
+            "glossary.yaml",
+            "--llm-concurrency",
+            "3",
+        ]
+    )
+
+    assert exit_code == 0
+    assert captured["llm_concurrency"] == 3