Released in Agent Eval 1.0.0; none of this is in 0.18.0. It applies to the generated EARS and RFC 2119 paths in
agent-judge-ai-core 1.0.0.What is measured, and where
- What: the whole request: the requirement headers plus the rendered prompt.
- Which builders:
EarsJury,Rfc2119Jury,EarsJudgeandRfc2119Judge, for single judges as well as rosters. - The default limit:
PromptLimits.DEFAULT_MAX_PROMPT_CHARACTERS, 100,000 characters. It is configurable.
Above the limit
No call is made. The result isERROR with reason code judge_failed, never FAIL: the requirement was not judged, so it has not failed. The reasoning states the size, the limit and the parts:
INCONCLUSIVE, retains no invocation because no call was made, and stores and reads back exactly through the requirement codecs.
Set another limit
Call.maxPromptCharacters(n) right after .runtime(...). The value must be positive; otherwise the builder throws IllegalArgumentException. Here judgeModel is the application’s configured EvalModel:
CompileGrammarTest (agent-judge-assertj) compiles. The behaviour is covered by PromptSizeGuardTests and PromptRefusalStorageTests.
Who must act
Behaviour change. A caller that pastes source or other large evidence into the workspace slot now getsERROR instead of a call. Pass a path the judge can read with its tools instead, or raise the limit.
See also Requirements judges and What’s New.