Skip to content

gen-ai: remove max_tokens from candidate inference config #1277

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
anup-deka merged 3 commits into from
Oct 21, 2026
Merged

gen-ai: remove max_tokens from candidate inference config #1277

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
bf3ab13
gen-ai: remove max_tokens from candidate inference config
potturu-vamsi Oct 21, 2026
59abbfc
gen-ai: simplify candidate inference config description
potturu-vamsi Oct 21, 2026
597fad5
Merge branch 'main' into vamsi/genai-eval-remove-max-tokens
anup-deka Oct 21, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 4 additions & 6 deletions specification/resources/gen-ai/definitions.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1534,12 +1534,10 @@ apiCandidateAgentConfig:
type: string
type: object
apiCandidateInferenceConfig:
description: Inference configuration for the candidate model during evaluation.
description: |-
Inference configuration for the candidate model during evaluation.
The output token limit is set automatically and cannot be configured.
properties:
max_tokens:
example: 123
format: int64
type: integer
reasoning_effort:
description: |-
Reasoning effort for reasoning-capable models (e.g. "low", "medium",
Expand Down Expand Up @@ -8165,7 +8163,7 @@ apiPresetSaveSection:

- PRESET_SAVE_SECTION_CANDIDATE: Candidate model identity (`candidate_model_uuid`, `candidate_model_source`,
`candidate_model_name`) and the non-prompt inference params
(`max_tokens`, `temperature`, `stop_token`).
(`temperature`, `stop_token`, `reasoning_effort`).
- PRESET_SAVE_SECTION_METRICS: The selected `metric_uuids` and the optional `star_metric`.
- PRESET_SAVE_SECTION_JUDGE: The `judge_model_uuid`.
- PRESET_SAVE_SECTION_DATASET: The `dataset_uuid`.
Expand Down
Loading