AI spam classification: the model's opinion as one bounded spam signal, and the llm_prompt Sieve function (AI-1 to AI-28)

The classifier sends only the subject and text, between unforgeable markers
after the operator's prompt, to an OpenAI-compatible endpoint the operator
configured; nothing is preset. Its answer maps to an LLM_ tag whose score is
clamped (+5.0, -1.0 by default) and can never discard or reject on its own;
X-Spam-LLM is sanitized, encoded and folded, and a planted one is removed.
Failures, timeouts past the ceiling, a full slot or a paused model leave
mail flowing untagged. llm_prompt answers trusted scripts, and accounts
holding interactAi within an hourly limit. Redirects aren't followed and no
content or secret is logged. The limits live in inbuxa:AiLimits.
Acceptance tests 1 and 3 to 21; test 2 as the re-enabled shared llm case,
whose setup no longer waits on a rules file from a developer's own path;
test 22 written as the ignored ai_compat.

crates/jmap-proto/src/request/mod.rs

@@ -113,6 +113,7 @@ pub enum GetRequestMethod {
     Registry(Box<GetRequest<Registry>>),
     MaskedEmail(Box<GetRequest<crate::object::fastmail_masked_email::FastmailMaskedEmail>>),
     DeletedAccount(Box<GetRequest<crate::object::inbuxa_deleted_account::DeletedAccount>>),
+    AiLimits(Box<GetRequest<crate::object::inbuxa_ai_limits::AiLimits>>),
 }
 
 #[derive(Debug)]
@@ -135,6 +136,7 @@ pub enum SetRequestMethod<'x> {
     Registry(Box<SetRequest<'x, Registry>>),
     MaskedEmail(Box<SetRequest<'x, crate::object::fastmail_masked_email::FastmailMaskedEmail>>),
     DeletedAccount(Box<SetRequest<'x, crate::object::inbuxa_deleted_account::DeletedAccount>>),
+    AiLimits(Box<SetRequest<'x, crate::object::inbuxa_ai_limits::AiLimits>>),
 }
 
 #[derive(Debug)]