@plurnk/plurnk-contracts 1.9.2 → 1.10.0

package/SPEC.md

@@ -224,7 +224,7 @@ framed-turn ::= turn | fence-open turn fence-close
 turn       ::= plan sep tail-0
 ```
 
-§gbnf-turn-shape The `gemma` transport root samples one complete
+§gbnf-turn-shape Neither rail admits an empty thought: the `gemma` channel body and the `qwen` think body each begin with at least one character, so a constrained call reasons before it acts. The `gemma` transport root samples one complete
 `<|channel>thought\n … <channel|>` enclosure. A Qwen-style chat template has
 already supplied `<think>\n` when the `qwen` transport root begins, so that root
 samples the body and required `</think>` closer. Each generated artifact declares
@@ -330,6 +330,15 @@ more horizontal whitespace characters before each slot and any permutation of
 the slots admitted by that operation, at most once each. Accepted spacing and
 permutation are not second canonical spellings.
 
+§heading-inline-body Text that follows the last slot on a heading line — after
+horizontal whitespace, beginning with a character that cannot open a slot (not `[`,
+`(`, or `<`) — is the first body line: `## EXEC0 [crm] (crm_query) {"soql": "…"}` and
+`## FIND0 (src/**) /createCoder/i` parse as their canonical two-line forms. Nothing is
+lost and the stored statement is canonical; the spelling is tolerated and announced:
+one warning-severity advisory follows the statement, naming the heading and the rule
+(body content goes immediately beneath the OP heading line), so the model learns
+the form from the packet and never from silent acceptance.
+
 §operation-annotation A heading may end with one single-line Markdown HTML
 comment. AstBuilder strips the delimiters and surrounding horizontal whitespace
 into the statement's fixed `annotation: string | null` field. The annotation is
@@ -421,6 +430,12 @@ to ACP v1
 [`schema-v1.21.0`](https://github.com/agentclientprotocol/agent-client-protocol/tree/schema-v1.21.0)
 commit `272bf799f35a258c6a4107a0410ed361e83683d3`.
 
+§exec-tag-signal EXEC's bracket slot names its runtime. A bracket whose first character is
+a sign is a tag signal instead — a runtime never starts with `+` or `-` — so
+`## EXEC0 [+fetch] (.)` and `## EXEC0 [crm] [+schema] (crm_describe)` admit: the tags
+classify the log row exactly as on FIND or READ, the runtime is the explicit one or the
+default shell, and each slot appears at most once.
+
 §log-tag-signal FIND, READ, EDIT, COPY, MOVE, and BARE canonically express additions
 as `+tag`. Because those operations have no tag-selection semantics, ANTLR also
 tolerates unsigned `tag` as an equivalent addition; `-tag` is invalid. Core
@@ -1142,7 +1157,9 @@ explicit `null` means roots. Singular and plural cardinalities are distinct
 contracts. Observation is not a client binding or permission grant.
 
 §application-loop-observation Loop observation exposes the durable scheduler
-state and exact terminal `OperationResult` for one owned Worker. Exterior
+state, exact terminal `OperationResult`, and exact count of packet-bearing
+Turns for one owned Worker. Packetless producer Turns and physical provider
+retries do not contribute to `packetCount`. Exterior
 adapters consume this projection instead of reconstructing lifecycle from
 events or persistence; events remain the live notification edge.
 
@@ -1208,10 +1225,11 @@ turn-shape imperatives (begin with `# PLAN0`, end with a terminal
   `## EXEC0 <-1,300>`” instead of a raw `unrecognized character`. The redirect is
   EXEC-scoped because its signal mode is exclusive; SEND/KILL are untouched.
 - §matcher-body-redirect **Matcher body in the slot region.** When the
-  post-target header region begins with `$`, `~`, or `@`, the lexer redirects
-  the unambiguous matcher to the first body line instead of returning the
-  generic slot list. Slash-led regex and XPath are excluded because `/` can be
-  target data.
+  post-target header region begins with `$`, `~`, or `@` with no whitespace
+  before it, the lexer redirects the unambiguous matcher to body content below the
+  OP heading instead of returning the generic slot list (after whitespace it is
+  already the inline body, {§heading-inline-body}). Slash-led regex and XPath are
+  excluded because `/` can be target data.
 - §combined-anchor-line-redirect **Combined anchor and line number in a scope.**
   A text-coordinate scope containing `@hash:L` or `@hash L` is one bounded hard
   error: `a scope position accepts one line coordinate; use the \`@hash\` anchor
@@ -1225,6 +1243,15 @@ turn-shape imperatives (begin with `# PLAN0`, end with a terminal
   \`[…]\` tag slot; a target goes in \`(…)\`. Try \`## EDIT0 (path)\``). It is
   gated on a path-shaped signal so a genuine additive-tag signal is not mis-steered
   toward a path it lacks.
+- §misplaced-annotation-advisory **Annotation in the body.** A READ or FIND whose
+  body is solely an HTML comment (`<!-- … -->`) can never carry a matcher: it is
+  the annotation the model put on the line below the heading. The builder takes
+  the comment as the annotation when the heading has none, builds the operation
+  with no body, and raises one warning-severity advisory naming what happened
+  and the correct form (`## READ0 (…) <…> <!-- … -->`); the parser places the
+  advisory right after its statement and the service delivers it as a
+  `parse_advisory` notice with its position. A body with any other content is a
+  matcher, as before.
 
 §error-shape The diagnostic class determines how much guidance the parser may
 provide:

package/dist/conformance/agui-v1.json

@@ -61,6 +61,29 @@
             "name": "ordinary-run",
             "events": [
                 { "type": "RUN_STARTED", "threadId": "fixture", "runId": "run" },
+                {
+                    "type": "STATE_SNAPSHOT",
+                    "snapshot": {
+                        "plurnk": {
+                            "status": {
+                                "lifecycle": "idle",
+                                "model": null,
+                                "loopId": null,
+                                "packetCount": 0,
+                                "activity": null
+                            }
+                        },
+                        "budget": {}
+                    }
+                },
+                {
+                    "type": "STATE_DELTA",
+                    "delta": [
+                        { "op": "replace", "path": "/plurnk/status/lifecycle", "value": "running" },
+                        { "op": "replace", "path": "/plurnk/status/loopId", "value": 1 },
+                        { "op": "replace", "path": "/plurnk/status/packetCount", "value": 1 }
+                    ]
+                },
                 {
                     "type": "CUSTOM",
                     "name": "plurnk.row",
@@ -73,6 +96,14 @@
                         "tx": { "body": "Work." }
                     }
                 },
+                {
+                    "type": "STATE_DELTA",
+                    "delta": [
+                        { "op": "replace", "path": "/plurnk/status/lifecycle", "value": "completed" },
+                        { "op": "replace", "path": "/plurnk/status/loopId", "value": 1 },
+                        { "op": "replace", "path": "/plurnk/status/activity", "value": null }
+                    ]
+                },
                 {
                     "type": "CUSTOM",
                     "name": "plurnk.terminated",
@@ -103,7 +134,7 @@
             ],
             "expect": {
                 "completion": "success",
-                "families": ["log/entry", "loop/terminated"],
+                "families": ["log/entry", "loop/packet", "loop/terminated"],
                 "status": 200
             }
         },

package/dist/plurnk.gemma.gbnf

@@ -114,7 +114,8 @@ rz-chan-b22 ::= ("<" rz-chan-b1 | [|chanl>toug\n] rz-chan-b0 | "e" rz-chan-b23 |
 rz-chan-b23 ::= ("<" rz-chan-b1 | [|chane>toug\n] rz-chan-b0 | "l" rz-chan-b24 | [^\x00-\x08\x0B-\x0C\x0E-\x1F\x7F<|chanel>toug\n] rz-chan-b0)?
 rz-chan-b24 ::= ("<" rz-chan-b1 | "|" rz-chan-b25 | [chanel>toug\n] rz-chan-b0 | [^\x00-\x08\x0B-\x0C\x0E-\x1F\x7F<|chanel>toug\n] rz-chan-b0)?
 rz-chan-b25 ::= ("<" rz-chan-b1 | [|chaneltoug\n] rz-chan-b0 | [^\x00-\x08\x0B-\x0C\x0E-\x1F\x7F<|chanel>toug\n] rz-chan-b0)?
-channel ::= "<|channel>thought\n" rz-chan-b0 "<channel|>"
+rz-chan-first ::= [0-9A-Za-z]
+channel ::= "<|channel>thought\n" rz-chan-first rz-chan-b0 "<channel|>"
 turn ::= plan tail-0
 framed-turn ::= turn | "```plurnk\n" turn "\n```"
 root-gemma ::= channel sep framed-turn

package/dist/plurnk.qwen.gbnf

@@ -102,7 +102,8 @@ rz-think-b10 ::= ("<" rz-think-b1 | [thnk>\n/] rz-think-b0 | "i" rz-think-b11 |
 rz-think-b11 ::= ("<" rz-think-b1 | [thik>\n/] rz-think-b0 | "n" rz-think-b12 | [^\x00-\x08\x0B-\x0C\x0E-\x1F\x7F<think>\n/] rz-think-b0)?
 rz-think-b12 ::= ("<" rz-think-b1 | [thin>\n/] rz-think-b0 | "k" rz-think-b13 | [^\x00-\x08\x0B-\x0C\x0E-\x1F\x7F<think>\n/] rz-think-b0)?
 rz-think-b13 ::= ("<" rz-think-b1 | [think\n/] rz-think-b0 | [^\x00-\x08\x0B-\x0C\x0E-\x1F\x7F<think>\n/] rz-think-b0)?
-qwen-tail ::= rz-think-b0 "</think>"
+rz-think-first ::= [0-9A-Za-z]
+qwen-tail ::= rz-think-first rz-think-b0 "</think>"
 turn ::= plan tail-0
 framed-turn ::= turn | "```plurnk\n" turn "\n```"
 root-qwen ::= qwen-tail sep framed-turn