Ronak Bhalgami

## Description This PR fixes the `resolution-too-deep` error that is causing all CI pipeline builds to fail during dependency installation. **Changes:** - Add upper bounds (

## Issue Description The CI pipeline is consistently failing during the dependency installation step with a `resolution-too-deep` error. This affects all PRs and prevents successful CI runs. ## Error Details...

## Description This PR adds support for the `reasoning_effort` parameter for OpenAI's reasoning models (o1, o3, and gpt-5 series). This parameter allows users to control the trade-off between reasoning depth...

## Description Fixes a critical bug where the memory system crashes with a PointStruct validation error when `event='NONE'` and only metadata needs to be updated. **Problem:** When adding duplicate memory...

fix: Use configured LLM model in categorization instead of hardcoded gpt-4o-mini

1

## Description This PR fixes a critical issue in OpenMemory's categorization function where the model was hardcoded to `gpt-4o-mini`, causing failures when users configured alternative LLM providers like SiliconFlow. **The...

feat: Add n1n API as LLM provider

3

## Description This PR adds support for [n1n API](https://n1n.ai/) as a new LLM provider in mem0. n1n is a robust API aggregation platform that provides access to 400+ large language...

Fix ArgumentCorrectnessMetric scoring logic for empty tool calls

1

## Issue Fixes #2242 ## Problem The `ArgumentCorrectnessMetric` incorrectly assigns a score of `1.0` (perfect score) when `tools_called` is empty. This is illogical because: - There are no tool calls...

prevent capteesys from duplicating output when -s disables global capture

1

## Summary Using the `capteesys` fixture with `-s` (`--capture=no`) printed output twice, even if the fixture wasn’t used in the test body. This issue is tracked in [[pytest-dev/pytest#13784](https://github.com/pytest-dev/pytest/issues/13784)](https://github.com/pytest-dev/pytest/issues/13784) and is...