v0.2.0
Added
- Self-correction guard for the query agent (
SelfCorrectingChatClient+UseAgentQLSelfCorrection). It wraps the function-invocation loop and re-prompts the model with a system reminder whenever a turn ends without an answer or an explicitReportFailure— restating the question and telling the model to read the query error, fix the SQL, and retry. AfterMaxAttemptsnudges it returns a configurable exhaustion message, so the agent never returns an empty answer. Enabled by default inAddAgentQLChat; tune it via the newconfigureSelfCorrectionparameter. - .NET test infrastructure (unit + integration) with the project restructured into
src/. - Integration tests isolated with Respawn.
See CHANGELOG.md.