stzLLMFunction

(no comment in the source: the name reads as a sentence) initno extension

(no comment in the source: the name reads as a sentence) name_no extension

(no comment in the source: the name reads as a sentence) set promptno extension

(no comment in the source: the name reads as a sentence) returns numberno extension

(no comment in the source: the name reads as a sentence) returns booleanno extension

(no comment in the source: the name reads as a sentence) returns stringno extension

(no comment in the source: the name reads as a sentence) returns one ofno extension

THE STRUCTURED RUNG. paFields is an stzOutputSchema declaration; it is compiled and judged HERE, so a defective declaration can never reach a model.QCSXTZZZIBWU

(no comment in the source: the name reads as a sentence) has schemano extension

A READ. Haro copies on assign, so configuring the returned schema configures a copy and nothing else -- use RefuseUnknownFields() below for the one knob that has to land on the stored one.no extension

Closed-world: a field the schema never declared refuses the answer instead of being reported and dropped.no extension

The findings the LAST validation produced, in the family's unified shape -- so a refusal can be handed to stzRuleReport.Ingest() and stand in the same CI gate as every other rule in the library.no extension

(no comment in the source: the name reads as a sentence) budgetno extension

(no comment in the source: the name reads as a sentence) set retriesno extension

TEST / OFFLINE DOOR, named for what it is. The responder is a FAKE standing where the model stands: it receives (prompt, attempt) and returns the raw text a model would have returned. It exists so the refusal paths -- the ones that matter most and that no seeded cache can reach -- can be narrated without a GGUF. It spends budget like a real call, and Why() says "FAKE responder" on every answer it produces, so nothing it returns can be mistaken for a live one. (The name follows stzGraphRule.UseChecker(): same escape-hatch shape, same word.)QCSXTZZZIBWU

(no comment in the source: the name reads as a sentence) is using responderno extension

(no comment in the source: the name reads as a sentence) calls madeno extension

(no comment in the source: the name reads as a sentence) whyno extension

the callalso written: Ofno extension

test/offline door: seed a known answer into the memo cache (the golden path for model-free environments; the seed is EXPLICIT)no extension

The prompt actually sent. For a structured function it carries the schema's own clause, so the model is ASKED for the shape rather than hoped at -- and the memo key is taken over this same text, so a seed and a call agree on what the question was.no extension

constrained decoding, asked and answered --------------------------- ON by default when a structure is declared and the engine enforces grammars. Turn it OFF to compare, or when a caller wants the model's unconstrained voice and the court's verdict on it.QCSXTZZZIBWU

Will the NEXT live call be grammar-constrained? Ask this rather than assuming: a nested structure, an off switch, or a build without the sampler rung all answer 0, and WhyNotConstrained() says which.no extension

(no comment in the source: the name reads as a sentence) why not constrainedno extension

The grammar text itself, for a reader who wants to see what was enforced.no extension

Was the LAST live answer grammar-constrained? (0 for a memo hit and for a fake responder -- neither of them decoded anything.)no extension

The sampling a RETRY uses. Attempt 1 never sees these -- it is greedy.QCSXTZZZIBWU

(no comment in the source: the name reads as a sentence) set max tokensQCSXTZZZIBWU

(no comment in the source: the name reads as a sentence) retry temperatureno extension

golden setsQCSXTZZZIBWU

Goldens hold STRUCTURES as readily as scalars now. Two things had to change for that, and both were real defects rather than gaps: Haro's own `=` answers 0 for two identical lists, so a structured golden could never have passed; and a failing structured case that reports only "expected / got" is unreadable, so the failure now carries the FIELD that moved.no extension