fix(llmp): strip integer min/max from non-OpenAI wire schemas#25
Merged
ethancjackson merged 1 commit intoJul 18, 2026
mainVectorInstitute/agentic-forecasting-live:mainfrom
schema-sanitizeVectorInstitute/agentic-forecasting-live:schema-sanitizeCopy head branch name to clipboard
Merged
fix(llmp): strip integer min/max from non-OpenAI wire schemas#25ethancjackson merged 1 commit intomainVectorInstitute/agentic-forecasting-live:mainfrom schema-sanitizeVectorInstitute/agentic-forecasting-live:schema-sanitizeCopy head branch name to clipboard
ethancjackson merged 1 commit into
mainVectorInstitute/agentic-forecasting-live:mainfrom
schema-sanitizeVectorInstitute/agentic-forecasting-live:schema-sanitizeCopy head branch name to clipboard
Conversation
Anthropic's structured-output validation rejects integer min/max (observed when WS_VERIFIER_MODEL routed the leakage-verification schema to claude: 252 failed predictions overnight, all cleanly skipped). Gemini tolerates the keys; constraints are enforced in prompt text and post-parse validation, so stripping them on the sanitized path is behavior-preserving. OpenAI-strict path unchanged. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Makes the WS_VERIFIER_MODEL ops lever actually usable: Anthropic rejects integer minimum/maximum in structured-output schemas (the LeakageVerification confidence field), which failed 252 predictions overnight when the verifier was pointed at sonnet during the gemini quota outage. The sanitized (non-OpenAI-strict) path now strips min/max alongside additionalProperties; enforcement lives in prompt + post-parse validation. GPT path verbatim as before. Suite green.
🤖 Generated with Claude Code