fix: whisper repetition loops, meeting transcript punctuation

- transcription: add temperature_inc=0 to whispercpp to disable fallback (prevents loops)
- pipeline: punctuate meeting transcript in one pass (parallel with summarize)
- output: write_meeting_docs accepts pre-built transcript_text
- llm: punctuate prompt preserves speaker labels

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

transcription.py

@@ -81,7 +81,10 @@ class TranscriptionEngine:
     ) -> Union[str, list[dict]]:
         async with httpx.AsyncClient(timeout=300) as client:
             with open(audio_path, "rb") as f:
-                data = {"language": language}
+                data = {
+                    "language": language,
+                    "temperature_inc": "0",   # disable fallback to prevent repetition loops
+                }
                 if with_segments:
                     data["response_format"] = "verbose_json"
                 r = await client.post(