Tracks how a malformed JSON response was repaired during prompt execution. Stored transiently on the prompt run entity and persisted into ValidationSummary JSON.
Which repair strategy succeeded
The original JSON parse error message
First 200 characters of the raw LLM output (for diagnostics)
Whether the JSON was repaired
Optional
The prompt run ID of the repair prompt execution (AI repair only)
Tracks how a malformed JSON response was repaired during prompt execution. Stored transiently on the prompt run entity and persisted into ValidationSummary JSON.