fix(title): strip <think> tags from title model responses and assistant context (#1927)

* fix(title): strip <think> tags from title model responses and assistant context

Reasoning models (e.g. minimax M2.7, DeepSeek-R1) emit <think>...</think>
blocks before their actual output. When such a model is used as the title
model (or as the main agent), the raw thinking content leaked into the thread
title stored in state, so the chat list showed the internal monologue instead
of a meaningful title.

Fixes #1884

- Add `_strip_think_tags()` helper using a regex to remove all <think>...</think> blocks
- Apply it in `_parse_title()` so the title model response is always clean
- Apply it to the assistant message in `_build_title_prompt()` so thinking
  content from the first AI turn is not fed back to the title model
- Add four new unit tests covering: stripping in parse, think-only response,
  assistant prompt stripping, and end-to-end async flow with think tags

* Fix the lint error

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
This commit is contained in:
Octopus
2026-04-14 09:51:39 +08:00
committed by GitHub
parent 053e18e1a6
commit c91785dd68
2 changed files with 54 additions and 1 deletions
@@ -1,6 +1,7 @@
"""Middleware for automatic thread title generation."""
import logging
import re
from typing import NotRequired, override
from langchain.agents import AgentState
@@ -77,7 +78,7 @@ class TitleMiddleware(AgentMiddleware[TitleMiddlewareState]):
assistant_msg_content = next((m.content for m in messages if m.type == "ai"), "")
user_msg = self._normalize_content(user_msg_content)
assistant_msg = self._normalize_content(assistant_msg_content)
assistant_msg = self._strip_think_tags(self._normalize_content(assistant_msg_content))
prompt = config.prompt_template.format(
max_words=config.max_words,
@@ -86,10 +87,15 @@ class TitleMiddleware(AgentMiddleware[TitleMiddlewareState]):
)
return prompt, user_msg
def _strip_think_tags(self, text: str) -> str:
"""Remove <think>...</think> blocks emitted by reasoning models (e.g. minimax, DeepSeek-R1)."""
return re.sub(r"<think>[\s\S]*?</think>", "", text, flags=re.IGNORECASE).strip()
def _parse_title(self, content: object) -> str:
"""Normalize model output into a clean title string."""
config = get_title_config()
title_content = self._normalize_content(content)
title_content = self._strip_think_tags(title_content)
title = title_content.strip().strip('"').strip("'")
return title[: config.max_chars] if len(title) > config.max_chars else title