Files
ai-podcast/backend/services/llm.py
tcpsyn 9d4b8a0d22 Replace token-based truncation with sentence-count limiting
- max_tokens back to 150 so LLM can finish thoughts
- New limit_sentences() keeps only first 2 complete sentences
- Never cuts mid-sentence — always ends at punctuation
- Applied to both chat and auto-respond paths

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-05 17:15:04 -07:00

6.4 KiB