mirror of
https://github.com/pydantic/pydantic-ai-harness.git
synced 2026-07-21 02:45:34 +00:00
LimitWarner rebuilds history each request, dropping any ModelRequest left with no parts after warning markers are stripped. An already-empty ModelRequest -- which pydantic-ai's empty-response retry appends when a model returns an empty response against a non-optional output type -- has no parts to begin with, so it was dropped too. That left history ending on a ModelResponse, and the next request failed the _agent_graph precondition with `UserError: Processed history must end with a ModelRequest`, killing the run. Keep a request that was already empty; only drop one that became empty because every part was a warning marker. Regression test covers the empty-response-retry tail. Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>