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
..
agent	feat: add a bare except to catch all errors	2025-06-21 15:34:02 +03:00
algo	Fix GPT-5 models to respect reasoning_effort config setting	2025-12-07 11:51:13 +08:00
git_providers	Merge pull request #2071 from BTLzdravtech/main	2025-11-16 07:18:20 +02:00
identity_providers	Fix typo in method parameter name	2025-05-15 18:42:08 +09:00
log	disable dynamic variables	2025-04-08 21:07:45 +03:00
secret_providers	chore: update secret more robustly	2025-06-02 13:48:47 +09:00
servers	Merge pull request #2071 from BTLzdravtech/main	2025-11-16 07:18:20 +02:00
settings	feat: improvements for Gitea integration	2025-10-19 16:00:01 +02:00
tools	Set a custom toml loader for Dynaconf (#2087)	2025-10-30 11:56:46 +02:00
__init__.py	Format files by pre-commit run -a	2024-10-30 10:00:36 +09:00
cli.py	Log a warning for pending asyncio tasks with coroutine details	2025-05-13 17:37:09 +09:00
cli_pip.py	adjustments to pypi	2024-03-23 16:16:32 +02:00
config_loader.py	Set a custom toml loader for Dynaconf (#2087)	2025-10-30 11:56:46 +02:00
custom_merge_loader.py	Set a custom toml loader for Dynaconf (#2087)	2025-10-30 11:56:46 +02:00