Require doc_type and summary in the AI output schema - #5
Merged
Conversation
Both were in the schema but not required, so the model omitted them under constrained generation and pydantic defaulted them to empty strings. Mark every field required (also makes the schema OpenAI strict-mode compliant / portable to cloud providers) and add minLength 1 to doc_type and summary so the model cannot satisfy the constraint with an empty string. date stays nullable; tags may be empty. Prompt updated to flag both as required. Verified live against a vision-enabled llama-server (Qwen3.6-35B + mmproj): doc_type now populated as drawing/receipt/invoice where it was previously blank. Co-Authored-By: Claude Opus 4.8 <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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes doc_type (and summary) coming back empty. Both were in the response schema but not in
required, so the model omitted them under constrained generation and pydantic defaulted them to empty strings.Change
required(also makes the schema OpenAI strict-mode compliant, so it's portable to cloud providers).doc_typeandsummarygetminLength: 1so the model can't satisfy the constraint with an empty string.datestays nullable;tagsmay be empty.Verified live
Against a vision-enabled llama-server (Qwen3.6-35B-A3B + mmproj), doc_type is now populated (
drawing/receipt/invoice) where it was previously blank on every run. summary is enforced the same way; the dateless drawing correctly has a null date.107 tests, 96% coverage, ruff clean.
🤖 Generated with Claude Code