Error Codes

datarelix.ai sorts errors into five classes for recovery UX:

NO_RESULTS — the question was understood but produced no useful data.
TIMEOUT — execution exceeded its time limit.
PLAN_FAILURE — the LLM could not produce a valid plan.
CONNECTION_FAILURE — the database could not be reached.
INTERNAL — generated SQL/code was invalid, sandbox crashed, or the LLM returned malformed output.

Every error event in the run stream carries an error_code that maps to one class.

NO_RESULTS

Code	Meaning	Recovery
`MISSING_TABLE`	Generated SQL references a table not in scope	Add the missing table to scope and retry.
`MISSING_COLUMN`	Generated SQL references a column that doesn’t exist	Check your table selection or rephrase.
`TYPE_MISMATCH`	Implicit cast failed	Rephrase to avoid mixing incompatible types.

The frontend surfaces these as “broaden your question” suggestions.

Code	Meaning	Recovery
`SQL_TIMEOUT`	Database query exceeded SQL_TIMEOUT (default 30s)	Add date filters or narrow scope.
`SANDBOX_TIMEOUT`	Sandbox Python step exceeded the wall-clock cap	Simpler analysis or reduce data volume.

Code	Meaning	Recovery
`NOT_ANSWERABLE`	LLM determined the question can’t be resolved with available data	Rephrase or add context.
`AMBIGUOUS_QUERY`	Multiple valid interpretations	Be more specific.

The frontend offers an editable retry — your question stays in the input ready to revise.

Code	Meaning	Recovery
`CONNECTION_ERROR`	Database unreachable	Test from sidebar; check credentials.

The frontend’s recovery banner has a “test connection” button.

Code	Meaning
`SQL_SYNTAX`	Generated SQL didn’t parse
`SQL_VALIDATION`	Generated SQL failed our validation rules
`SQL_EXECUTION`	Database returned an error
`SANDBOX_CODE_ERROR`	Python in the sandbox raised
`SANDBOX_OOM`	Python in the sandbox exceeded memory cap
`LLM_INVALID_OUTPUT`	LLM returned malformed IR

Most internals trigger an automatic repair attempt up to the configured budget. After the budget is exhausted you’ll see the underlying error.