ilia/nanobot
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

Merge pull request #617 from themavik/fix/523-clamp-max-tokens

Browse Source 
fix(providers): clamp max_tokens to >= 1 before calling LiteLLM
This commit is contained in:
Xubin Ren 2026-02-14 18:02:20 +08:00 committed by GitHub
commit 3411035447
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
nanobot/providers/litellm_provider.py
View File

@ -122,6 +122,10 @@ class LiteLLMProvider(LLMProvider):
""" """
model = self._resolve_model(model or self.default_model) model = self._resolve_model(model or self.default_model)
# Clamp max_tokens to at least 1 — negative or zero values cause
# LiteLLM to reject the request with "max_tokens must be at least 1".
max_tokens = max(1, max_tokens)
kwargs: dict[str, Any] = { kwargs: dict[str, Any] = {
"model": model, "model": model,
"messages": messages, "messages": messages,