Tyler Zhang eb2f432e16 Fix GPT-5 models to respect reasoning_effort config setting ... Previously, GPT-5 models had reasoning_effort hardcoded to 'minimal', which caused two issues: 1. 'minimal' is not supported by some models (e.g., gpt-5.1-codex) 2. User's config.reasoning_effort setting was completely ignored This fix: - Reads and respects user's reasoning_effort config value - Uses valid defaults: 'none' for non-thinking models, 'low' for thinking - Adds logging to show which value is being used Fixes #2120		2025-12-07 11:51:13 +08:00
..
ai_handlers	Fix GPT-5 models to respect reasoning_effort config setting	2025-12-07 11:51:13 +08:00
__init__.py	feat: add OpenAI GPT-5.1 series models	2025-11-17 00:14:05 +08:00
cli_args.py	cleanup	2025-03-20 21:49:19 +02:00
file_filter.py	fix: add error handling to bitbucket file filtering	2025-07-21 10:15:57 +00:00
git_patch_processing.py	Add multi-model support for different reasoning tasks	2025-04-27 11:00:34 +03:00
language_handler.py	Add filter for files with bad extensions in language handler	2025-03-11 17:03:05 +02:00
pr_processing.py	Update pr_agent/algo/pr_processing.py	2025-10-10 20:44:31 +09:00
token_handler.py	Fix: use ModelTypeValidator static methods directly	2025-05-25 18:00:38 +09:00
types.py	feat: add dedent option to code snippet formatting	2024-12-24 07:49:27 +02:00
utils.py	Tr/updates23 (#2008)	2025-08-22 10:16:08 +03:00