@plurnk/plurnk-grammar 0.68.0 → 0.71.0

package/README.md

@@ -201,9 +201,9 @@ Errors are JSON-serializable. Shape: `{ line, column, source, message }` where `
 
 One generated [GBNF](https://github.com/ggml-org/llama.cpp/blob/master/grammars/README.md) grammar ships for llama.cpp constrained sampling, calibrated for the Fireworks/DeepSeek backend:
 
-- **`plurnk.gbnf` (PLAN-anchored turn)** — `root ::= preplan plan sep batch-step* send-final-any sep`. A Plurnk turn is a `*:PLAN:OPS:SEND[N]` sandwich: a FREE reasoning preamble (any text up to the first `<<PLAN`), then a MANDATORY `<<PLAN` anchoring a strict ops-only batch (bounded `WS{0,7}` separators, no free prose between), closed by exactly one terminal `SEND[102|200|202|300|499]` — structural termination (forced EOS), not an optional stop a near-greedy decoder can sail past.
+- **`plurnk.gbnf` (PLAN-anchored turn)** — `root ::= preplan plan sep batch-step* send-final-any sep`. A Plurnk turn is a `*:PLAN:OPS:SEND[N]` sandwich: a FREE **op-free** reasoning preamble, then a MANDATORY `<<PLAN` anchoring a strict ops-only batch (bounded `WS{0,7}` separators, no free prose between), closed by exactly one terminal `SEND[102|200|202|300|499]` — structural termination (forced EOS), not an optional stop a near-greedy decoder can sail past.
 
-The preamble names **no reasoning delimiter** — it admits any text completing no `<<PLAN`. That keeps it format-agnostic across models and, crucially, never masks a model's native reasoning token: the model reasons freely (a reasoning model's CoT separates into `reasoning_content`; a non-reasoning model reasons in the `<<PLAN` body, the public statement of intent), then the mandatory `<<PLAN` anchors the strict turn. `PlurnkParser` discards everything before the first `<<PLAN`. The parser remains the permissive contract over the actionable turn: everything the grammar can generate, the parser accepts (and much it doesn't: word suffixes, richer slot internals).
+The preamble names **no reasoning delimiter** — it admits any text completing no `<<OP` opener. That keeps it format-agnostic across models and never masks a model's native reasoning token: the model reasons freely (a reasoning model's CoT separates into `reasoning_content`; a non-reasoning model reasons in the `<<PLAN` body, the public statement of intent), then `<<PLAN` anchors the strict turn. The **ANTLR grammar enforces the same sandwich**: `PlurnkParser.parse(input)` parses a turn — free text before PLAN, a required PLAN, nothing but whitespace between/after ops, and a required terminal SEND; a packet without a PLAN *and* a terminal SEND is invalid. A Plurnk packet IS a turn — there is no permissive fallback. `PlurnkParser.parseStatements(input)` parses a bare statement sequence (teaching-example collections, single ops); it is not for model output.
 
 ```ts
 import.meta.resolve("@plurnk/plurnk-grammar/plurnk.gbnf")