Skip to main content
Schema-Triggered Patch automatically patches existing data when the MCP/schema is updated — reconciling records to align with the new schema without a full regeneration. When function implementations or names have changed, instead of regenerating an entire dataset from scratch, you provide a function mapping that specifies which functions have changed, and the system regenerates only the affected dialogue segments.

​
When to Use

  • Function names have been renamed (e.g., getUser to fetchUser)
  • Function implementations have changed and existing conversations need to reflect the new behavior
  • You want to update a subset of conversations without losing the overall dataset structure

​
Parameters

ParameterRequiredDescription
inputYesPath to existing data file or directory
function_mappingYesJSONL file mapping previous function names to new function names
requestYesDescription of regeneration instructions
mcp_server_urlYesURL of the MCP server providing the updated schema
domainNoDomain context for regeneration
reference_docNoPath to reference documentation

​
Function Mapping File

The function mapping is a JSONL file where each line maps a previous function name to its new name. This tells the system which conversation segments need regeneration. 
{"previous": "getUser", "new": "fetchUser"}
{"previous": "createOrder", "new": "submitOrder"}
This feature uses the standard chatbot interaction flow. Describe what you need in natural language, and the CLI guides you through parameter collection and confirmation.

​
Using /execute

You can also run schema-triggered-patch non-interactively via /execute with a YAML config: 
task: schema-triggered-patch
input: ./data/conversations.jsonl
function_mapping: ./mappings/function_changes.jsonl
request: Regenerate only the affected dialogue segments based on the function mapping.
domain: airline customer service
mcp_server_url: http://127.0.0.1:8009

​
Output

After a run completes, results are saved under outputs/ as a new run directory, for example:
  • outputs/schema-triggered-patch_output_<run_id>/
Inside the run directory:
  • generated_data.jsonl - The regenerated dataset in JSONL format
  • datapoints/ - One JSON file per sample (expanded view of generated_data.jsonl)
  • metadata.json - Run metadata (task type, parameters, primary files, timestamps)
The viewer provides a split view that shows regenerated segments alongside the original data for easy comparison.