Daniel O'Connell 21dedbeb61 Fix search score aggregation to use mean instead of sum ...

BUG-004: Score aggregation was broken - documents with more chunks
would always rank higher regardless of relevance because scores were
summed instead of averaged.

Changes:
- Changed score calculation from sum() to mean()
- Added comprehensive tests for SearchResult.from_source_item()
- Added tests for elide_content helper

This ensures search results are ranked by actual relevance rather
than by the number of chunks in the document.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

2025-12-19 18:25:15 +01:00

..

data

better emails embedding + format search results

2025-06-09 13:51:58 +02:00

integration

fix tests

2025-06-10 15:32:34 +02:00

memory

Fix search score aggregation to use mean instead of sum

2025-12-19 18:25:15 +01:00

providers

fix linting

2025-05-20 22:54:45 +02:00

tools

add a bunch of tests

2025-11-03 23:23:41 +01:00

__init__.py

initial structure

2025-04-27 14:31:53 +02:00

conftest.py

Add pytest markers for fast/slow test separation

2025-12-19 18:21:41 +01:00