Sydney Runkle 3030ffc248 fix: simplify summarization cutoff logic (#34195) ...

This PR changes how we find the cutoff for summarization, summarizing
content more eagerly if the initial cutoff point isn't safe (ie, would
break apart AI + tool message pairs)

This new algorithm is quite simple - it looks at the initial cutoff
point, if it's not safe, moves forward through the message list until it
finds the first non tool message.

For example:

```
H
AI
TM
--- theoretical cutoff based keep=('messages', 3)
TM
AI
TM
```

```
H
AI
TM
TM
--- actual cutoff, more aggressive summarization
AI
TM
```

2025-12-04 12:44:50 -05:00

..

cassettes

fix(langchain, openai): fix create_agent / response_format for Responses API (#33939)

2025-11-13 10:18:15 -05:00

integration_tests

fix(langchain, openai): fix create_agent / response_format for Responses API (#33939)

2025-11-13 10:18:15 -05:00

unit_tests

fix: simplify summarization cutoff logic (#34195)

2025-12-04 12:44:50 -05:00

__init__.py

…