# X_LLM_TRUNCATED

## Means

the answer hit its `maxTokens` ceiling before it was complete

## Typical cause

the ceiling is below what the output schema asks for; the stop reason is read before the schema, so a cut-off answer is never accepted

## Fix

set `maxTokens:` on the `llm()` or `agent()` declaration to double the ceiling the `fix:` names, or drop fields from its `output` schema

[MCP and AI](/error-codes#mcp-and-ai)