Files
hermes-agent/tests
shawchanshek 3b739b990b fix(title_generator): strip think blocks from LLM output before extracting title
Think-enabled models (MiniMax M2.7, DeepSeek, etc.) emit inline
<think>...</think> reasoning even for simple prompts like title
generation, and the raw XML was leaking into session titles. Route the
title-model response through the canonical strip_think_blocks scrubber
before cleanup so every tag variant — closed pairs, unterminated blocks,
orphan closes, mixed case — is handled, not just a single literal
<think> pair.

- 2 regression tests: closed <think> pair stripped, unterminated block
  at start yields no title.

Salvaged from PR #44126 by @shawchanshek.
2026-07-01 04:18:48 -07:00
..