scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-07 02:59:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 103

fix(friendli): emit explicit False for removed reasoning-effort flags

Browse source 
Greptile P1: _effort_flags only wrote True for enabled levels, so
sync_local_data_with_remote's merge left stale True flags when
Friendli dropped an effort level from reasoning_options.
This commit is contained in:
siyoon 2026-08-22 12:47:13 +09:00
parent 82b9ba8c77
commit 471440eb79
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
.github/scripts/auto_update_price_and_context_window_file.py vendored
View file

@ -73,7 +73,7 @@ def _find_base_model_entry(base_model: str, local_data: dict) -> Optional[str]:
def _effort_flags(reasoning_options: list) -> dict:
flags: dict[str, bool] = {}
flags: dict[str, bool] = {flag: False for flag in EFFORT_FLAG_MAP.values()}
for opt in reasoning_options or []:
if opt.get("type") == "effort":
for val in opt.get("values", []):