phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-14 07:52:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: Add max_output_tokens to Response API

Browse source 
Responses and Completions have a max_output_tokens field. It is currently
missing from the create and response object in Responses API.

This PR fixes it.

fixes: #3562
Signed-off-by: Abhishek Bongale <abhishekbongale@outlook.com>
This commit is contained in:
Abhishek Bongale 2025-10-06 09:46:09 +01:00
parent 92219fd8fb
commit bb58da22a1
14 changed files with 127 additions and 20 deletions
Download patch file Download diff file Expand all files Collapse all files

11
docs/static/llama-stack-spec.html vendored
View file

@ -7503,6 +7503,10 @@
"type": "string",
"description": "(Optional) Truncation strategy applied to the response"
},
"max_output_tokens": {
"type": "integer",
"description": "(Optional) Upper bound for response tokens generation"
},
"input": {
"type": "array",
"items": {
@ -8009,6 +8013,9 @@
},
"max_infer_iters": {
"type": "integer"
},
"max_output_tokens": {
"type": "integer"
}
},
"additionalProperties": false,
@ -8078,6 +8085,10 @@
"truncation": {
"type": "string",
"description": "(Optional) Truncation strategy applied to the response"
},
"max_output_tokens": {
"type": "integer",
"description": "(Optional) Upper bound for response tokens generation"
}
},
"additionalProperties": false,