phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-03 09:53:45 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix: Avoid BadRequestError due to invalid max_tokens (#3667)

Browse source 
This patch ensures if max tokens is not defined, then is set to None
instead of 0 when calling openai_chat_completion. This way some
providers (like gemini) that cannot handle the `max_tokens = 0` will not
fail

Issue: #3666
This commit is contained in:
Luis Tomas Bolivar 2025-10-27 17:27:21 +01:00 • committed by GitHub
parent 00d8414597
commit f18b5eb537
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
171 changed files with 12728 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

1
docs/static/deprecated-llama-stack-spec.html vendored
View file

@ -3901,7 +3901,6 @@
},
"max_tokens": {
"type": "integer",
"default": 0,
"description": "The maximum number of tokens that can be generated in the completion. The token count of your prompt plus max_tokens cannot exceed the model's context length."
},
"repetition_penalty": {

1
docs/static/deprecated-llama-stack-spec.yaml vendored
View file

@ -2862,7 +2862,6 @@ components:
description: The sampling strategy.
max_tokens:
type: integer
default: 0
description: >-
The maximum number of tokens that can be generated in the completion.
The token count of your prompt plus max_tokens cannot exceed the model's

1
docs/static/experimental-llama-stack-spec.html vendored
View file

@ -2376,7 +2376,6 @@
},
"max_tokens": {
"type": "integer",
"default": 0,
"description": "The maximum number of tokens that can be generated in the completion. The token count of your prompt plus max_tokens cannot exceed the model's context length."
},
"repetition_penalty": {

1
docs/static/experimental-llama-stack-spec.yaml vendored
View file

@ -1695,7 +1695,6 @@ components:
description: The sampling strategy.
max_tokens:
type: integer
default: 0
description: >-
The maximum number of tokens that can be generated in the completion.
The token count of your prompt plus max_tokens cannot exceed the model's

1
docs/static/stainless-llama-stack-spec.html vendored
View file

@ -15452,7 +15452,6 @@
},
"max_tokens": {
"type": "integer",
"default": 0,
"description": "The maximum number of tokens that can be generated in the completion. The token count of your prompt plus max_tokens cannot exceed the model's context length."
},
"repetition_penalty": {

1
docs/static/stainless-llama-stack-spec.yaml vendored
View file

@ -11600,7 +11600,6 @@ components:
description: The sampling strategy.
max_tokens:
type: integer
default: 0
description: >-
The maximum number of tokens that can be generated in the completion.
The token count of your prompt plus max_tokens cannot exceed the model's