EBNF de AXON — referencia abreviada de la gramática

Esta página reproduce las reglas de producción que un agente necesita más a menudo: estructura del programa, declaraciones, cuerpo de un flow, expresiones de tipo y el fragmento de tipos de sesión.

El EBNF canónico completo vive en el paper del lenguaje papers/paper_axon_language.md; la implementación del parser vive en axon-frontend/src/parser.rs. Esta versión abreviada está curada para que la consuma un agente: los tokens que importan, las producciones que compilan y las omisiones marcadas con claridad.

Superficie léxica

identifier        = letter , { letter | digit | "_" } ;
integer           = digit , { digit } ;
number            = integer , [ "." , digit , { digit } ] ;
duration          = integer , ( "ms" | "s" | "m" | "h" ) ;
string_literal    = '"' , { utf8_char } , '"' ;
bcp47             = '"' , language_subtag , { "-" , subtag } , '"' ;

Los comentarios son de línea, con //. El espacio en blanco no es significativo salvo donde la gramática de slugs con puntos (legal:HIPAA.164_502) exige adyacencia entre tokens.

Programa

program           = { declaration | import | run } ;
import            = "import" , identifier , "{" , identifier_list , "}" ;
declaration       = persona_def
                  | context_def
                  | flow_def
                  | anchor_def
                  | tool_def
                  | type_def
                  | session_def
                  | socket_def
                  | axonendpoint_def
                  | axonstore_def
                  | shield_def
                  | mandate_def
                  | compute_def
                  | lambda_def
                  | daemon_def
                  | (* …65+ total — see axon://grammar/top_level *) ;
run               = "run" , identifier , "(" , arg_list? , ")"
                  , [ "as" , identifier ]
                  , [ "within" , identifier ]
                  , [ "constrained_by" , "[" , identifier_list , "]" ]
                  , [ "on_failure" , ":" , failure_policy ]
                  , [ "output_to" , ":" , string_literal ]
                  , [ "effort" , ":" , effort_level ] ;

Persona

persona_def       = "persona" , identifier , "{" , persona_field+ , "}" ;
persona_field     = "domain"               , ":" , string_list
                  | "tone"                 , ":" , tone_ident
                  | "confidence_threshold" , ":" , number
                  | "cite_sources"         , ":" , bool
                  | "refuse_if"            , ":" , bracketed_identifiers
                  | "language"             , ":" , bcp47
                  | "description"          , ":" , string_literal ;

tone_ident        = "analytical" | "assertive" | "casual" | "diplomatic"
                  | "empathetic" | "formal"    | "friendly" | "precise" ;

Flow + step

flow_def          = "flow" , identifier , "(" , param_list? , ")"
                  , [ "->" , type_expr ]
                  , "{" , { flow_step } , "}" ;
param_list        = parameter , { "," , parameter } ;
parameter         = identifier , ":" , type_expr ;

flow_step         = step_node
                  | if_stmt | for_stmt | let_stmt | return_stmt
                  | break_stmt | continue_stmt
                  | reason_step | probe_step | validate_step | refine_step
                  | weave_step | use_step | par_block | hibernate_step
                  | listen_step | retrieve_step | persist_step | mutate_step
                  | deliberate_step | navigate_step | drill_step | trail_step
                  | (* …complete list in parser.rs::parse_flow_step *) ;

deliberate_step   = "deliberate" , "{" , { flow_step } , "}" ;
(* v2.12.0/63 — cognitive retrieval over a `pix` tree OR a `corpus`
   graph (a corpus WITH `relations:` is an MDN graph). Dispatch is by
   the referenced declaration, not by keyword. *)
navigate_step     = "navigate" , identifier
                  , "{" , { navigate_field } , "}" ;
navigate_field    = "query"  , ":" , expression
                  | "from"   , ":" , identifier        (* seed document *)
                  | "budget" , ":" , number            (* max documents  *)
                  | "trail"  , ":" , boolean
                  | "output" , ":" , identifier ;
drill_step        = "drill"  , identifier , "{" , { navigate_field } , "}" ;
trail_step        = "trail"  , identifier , "{" , { navigate_field } , "}" ;

step_node         = "step" , identifier , [ "use" , identifier ]
                  , "{" , step_field+ , "}" ;
step_field        = "given"            , ":" , expression
                  | "ask"              , ":" , string_literal
                  | "output"           , ":" , type_expr
                  | "confidence_floor" , ":" , number
                  | "navigate"         , ":" , dotted_identifier
                  | "apply"            , ":" , identifier
                  | sub_construct ;
sub_construct     = ( "use" | "probe" | "reason" | "weave" | "stream" ) , … ;

reason_step       = "reason" , [ identifier ] , [ "{" , (* skipped *) , "}" ] ;

Expresiones de tipo

type_expr         = identifier , [ "<" , type_expr , ">" ] , [ "?" ] ;
type_def          = "type" , identifier
                  , [ "(" , number , ".." , number , ")" ]
                  , [ "where" , expression ]
                  , [ "compliance" , bracketed_identifiers ]
                  , [ "{" , type_field_list , "}" ] ;
type_field_list   = type_field , { "," , type_field } ;
type_field        = identifier , ":" , type_expr ;

Los genéricos recursivos como FlowEnvelope<List<TenantRecord>> se aceptan desde la v2.0.0.

Anchor

anchor_def        = "anchor" , identifier , "{" , anchor_field+ , "}" ;
anchor_field      = "require"          , ":" , identifier
                  | "reject"           , ":" , bracketed_identifiers
                  | "enforce"          , ":" , identifier
                  | "description"      , ":" , string_literal
                  | "confidence_floor" , ":" , number
                  | "unknown_response" , ":" , string_literal
                  | "on_violation"     , ":" , violation_policy ;
violation_policy  = ( "raise" | "fallback" ) , identifier
                  | identifier ;

Tool

tool_def          = "tool" , identifier , "{" , tool_field+ , "}" ;
tool_field        = "provider"    , ":" , identifier
                  | "max_results" , ":" , integer
                  | "filter"      , ":" , filter_expr
                  | "timeout"     , ":" , duration
                  | "runtime"     , ":" , identifier
                  | "sandbox"     , ":" , bool
                  | "effects"     , ":" , effect_row ;
effect_row        = "<" , effect_term , { "," , effect_term } , ">" ;
effect_term       = effect_name , [ ":" , qualifier_value ] ;
effect_name       = "io" | "network" | "pure" | "random" | "storage"
                  | "stream" | "trust" | "sensitive" | "legal" | "ots" ;
qualifier_value   = dotted_slug ;

Tipos de sesión (v2.3.0)

session_def       = "session" , identifier , "{"
                  , "client" , ":" , session_type
                  , "server" , ":" , session_type
                  , "}" ;
session_type      = "[" , session_action , { "," , session_action } , "]" ;
session_action    = "send" , type_expr
                  | "receive" , type_expr
                  | "select" , "{" , session_branch , { "," , session_branch } , "}"
                  | "branch" , "{" , session_branch , { "," , session_branch } , "}"
                  | "loop"
                  | "end" ;
session_branch    = identifier , ":" , session_type ;

socket_def        = "socket" , identifier , "{" , socket_field+ , "}" ;
socket_field      = "protocol"      , ":" , identifier
                  | "backpressure"  , ":" , "credit" , "(" , integer , ")"
                  | "reconnect"     , ":" , "cognitive_state"
                  | "legal_basis"   , ":" , identifier ;

Las restricciones de dualidad y de contrapresión refinada por créditos (peer ≡ self⊥, descarga de Presburger) viven en el verificador de tipos, no en la gramática — son reglas de tipado, que se aplican después de que el parser haya producido el AST.

Qué NO incluye esta página

Esta es la referencia abreviada de la gramática. Producciones omitidas a propósito (cubiertas en recursos dedicados o en el paper):

• La enumeración completa de flow_step (~30 tipos o más — la lista canónica está en parser.rs::parse_flow_step).
• Las declaraciones completas de axonendpoint, axonstore, daemon, shield, psyche, ots, agent, lambda, compute, resource, fabric, manifest, observe, reconcile, lease, ensemble, pix, mandate, mcp, taint, logic, corpus y dataspace.
• La gramática de slugs con puntos para anotaciones de cumplimiento (cubierta bajo cada recurso axon://compliance/<framework>).
• Las reglas de proyección multiparte de Honda-Yoshida-Carbone (cubiertas bajo axon://logic/session_duality y el paper de la v2.3.0).

Para esas producciones, consulta las fuentes enlazadas o los recursos por primitiva vía axon.primitives + axon.primitive_doc.