dearwolf/aider
1
0
Fork 0
mirror of https://github.com/Aider-AI/aider.git synced 2025-05-31 01:35:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 9

avoid stomping extra_params[max_tokens]=1 in cache warming, which causes loop of 1 token infinite-output responses with prefill models #1842 #1841

Browse source
This commit is contained in:
Paul Gauthier 2024-09-30 14:22:11 -07:00
parent 8fb0362b47
commit f2e1e17741
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
aider/coders/base_coder.py
View file

@ -1073,7 +1073,7 @@ class Coder:
self.warming_pings_left -= 1
self.next_cache_warm = time.time() + delay
kwargs = self.main_model.extra_params or dict()
kwargs = dict(self.main_model.extra_params) or dict()
kwargs["max_tokens"] = 1
try: