Skip to main content
The Response Healing plugin automatically validates and repairs malformed JSON responses from AI models. When models return imperfect formatting – missing brackets, trailing commas, markdown wrappers, or mixed text – this plugin attempts to repair the response so you receive valid, parseable JSON.

​
Overview

Response Healing provides:
  • Automatic JSON repair: Fixes missing brackets, commas, quotes, and other syntax errors
  • Markdown extraction: Extracts JSON from markdown code blocks

​
How It Works

The plugin activates for non-streaming requests when you set text.format in a Responses API request (or response_format on Chat Completions) to either type: "json_schema" or type: "json_object", and include the response-healing plugin in your plugins array. See the Complete Example below for a full implementation.

​
What Gets Fixed

The Response Healing plugin handles common issues in LLM responses:

​
JSON Syntax Errors

Input: Missing closing bracket
Output: Fixed

​
Markdown Code Blocks

Input: Wrapped in markdown
Output: Extracted

​
Mixed Text and JSON

Input: Text before JSON
Output: Extracted

​
Trailing Commas

Input: Invalid trailing comma
Output: Fixed

​
Unquoted Keys

Input: JavaScript-style
Output: Fixed

​
Complete Example

​
Limitations

Non-Streaming Requests OnlyResponse Healing only applies to non-streaming requests.
Will not repair all JSONSome malformed JSON responses may still be unrepairable. In particular, if the response is truncated by max_output_tokens, the plugin will not be able to repair it.