feat(suite): expose provider sampling options - #23
Open
vsolano9 wants to merge 1 commit into
Open
Conversation
Add validated suite- and case-level temperature and maxTokens fields, resolve them with case-over-suite precedence, and retain temperature zero as the deliberate deterministic default. Document the public format, update both examples, and cover parsing, validation, precedence, and provider request forwarding offline. Closes AgentPostmortem#17
Author
|
Postflight clarification for the red
The independent Node 20/22 CI run passed typecheck, lint, build, all 76 tests, and the example smoke on this exact head. Runs: quality comparison · Node 20/22 CI |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Closes #17.
Suites and cases can now declare
temperatureandmaxTokens. Case values override suite defaults; absent temperature deliberately resolves to0for reproducible regression runs, while an absent token cap remains omitted.The loader rejects negative/non-finite temperatures and non-positive/non-integer token caps at both levels. README and both bundled suites demonstrate the public fields, including case overrides.
Validation:
git diff --checkAll validation is offline and mock-first; no provider key or network model call is used.