The llama-server tool, specifically version b10868, exhibits a bug where it fails to enforce schema constraints when the `response_format` is set to `json_schema` with a schema directly nested under `response_format`. Instead of applying the provided schema, the server returns unconstrained text, similar to when no `response_format` is specified. This issue is particularly insidious because the server still returns an HTTP 200 status code and logs no errors, making it difficult to detect. A previous fix in March 2025 addressed a similar issue but only for a nested `json_schema` structure, leaving the direct `response_format.schema` case unaddressed. AI
IMPACT This bug could lead to unexpected data formatting issues in applications relying on llama-server for structured output.
RANK_REASON Bug report on a specific tool's functionality.
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →