UAI-1 es la norma pública actual de mensajes para comunicación estructurada de IA a IA.
UAIX shield mark Carta pública de interoperabilidad UAIX.org 通用人工智能交换 Publicación pública de normas
Actual UAI-1
  • Versión actual UAI-1
  • Definición en lenguaje claro Formato de mensaje abierto para intercambio IA-a-IA auditable
  • Atribución actual Michael Joseph Kappel, MCP
  • Empiece aquí Inicio, Traspaso de proyecto, UAI-1, validador, hoja de ruta y registro de cambios

Compatibilidad de agentes

Validator Rules

Agent compatibility validator failures and warnings for GET-Action fallback, idempotency, query secrets, JavaScript-only discovery, llms.txt, POST equivalents, and no-op behavior.

  • Record UAIX-DOC-2754
  • Path /es-es/spec/validator-rules/
  • Use Canonical public record

Document status

Public standards page Published on UAIX as part of the current public standards record
Code
UAIX-DOC-2754
Surface
Compatibilidad de agentes
Access
Public and linkable

如何使用本页

Use this page as part of the current Compatibilidad de agentes public record, then follow its linked standards pages for the next step.

Agent compatibility validation checks the lowest advertised capability first. Rich interfaces pass only when lower-capability discovery is honest and bounded.

Required failures

  • get_action_fallback_required: L0/L1 compatibility fails when a core writable action is POST-only and no documented GET fallback or no-op URL exists.
  • get_action_idempotency_required: GET-Action fails when a write-capable example lacks idempotency_key or nonce.
  • get_action_query_secret: GET-Action fails when examples put secrets, tokens, passwords, account identifiers, medical identifiers, payment data, private messages, or regulated identifiers in URLs.
  • get_action_js_only_discovery: GET-Action fails when discovery is hidden behind JavaScript-only UI.
  • llms_minimal_instruction_required: L0/L1 discovery fails when llms.txt points only to complex OpenAPI or tool specs and omits direct minimal instructions.
  • retry_loop_no_op_violation: no-op handling fails when unsupported agents are told to keep retrying or guessing.

Required warnings

  • post_equivalent_recommended: warn when a GET-Action has no POST or OpenAPI equivalent for capable clients.
  • get_action_security_order_warning: warn when examples appear before consent and security boundaries.
  • side_effecting_get_discovery_warning: warn when side-effecting GET links are presented as general discovery shortcuts.
  • browser_form_fallback_required: warn when browser-targeted POST guidance lacks a visible form or browser-open fallback.
  • restore_readback_required: warn when create/update guidance lacks a restore or readback URL and forces endpoint guessing.
  • dashboard_default_path_warning: warn when dashboard or custom-template paths are presented as default while generated profile or package paths exist.
  • post_blocked_fallback_required: warn when a POST path omits fallback behavior for agents that cannot execute arbitrary JSON POST.
  • live_get_blocked_fallback_required: warn when dynamic GET guidance targets chatbot-level agents without declaring live HTTP GET and a fallback for indexed-only fetchers.

Test fixtures

The release publishes positive and negative fixture JSON records for these rule families under the UAI-1 examples tree and exposes the rule catalog through agent-compatibility.json.

代理可执行性矩阵

可执行指导不只是端点发现。 路由 records should name the ability level, method, content type, side-effect status, fetch execution class, required fields, result URL field, restore/readback URL field, write credential response path, browser-form equivalent, GET safety, POST-blocked fallback, and live-GET-blocked fallback.

Level Executable path Required route guidance
L0 Read-only route discovery Static page, sitemap, llms.txt, or public GET route names the next public URL or no-op review URL.
L1 Manifest/schema discovery Machine record names schema, safe-read status, whether live dynamic GET is required, unsupported actions, and capability limits.
L2 Browser-open plus form submission Browser-targeted writes provide a visible form or browser-open workflow when browser agents are a target.
L3 Structured HTTP JSON POST POST route names content type, required fields, result URL, restore/readback URL, and structured errors.
L4 Authenticated owned mutation Owned mutation names write credential response path, secret handling, audit, expiry, and idempotency.
L5 Restore/readback verification Create or update flow exposes a public-safe restore/readback route.
L6 Multi-agent handoff/reporting Handoff names task history, owner, role, blocker/no-op behavior, final report, and evidence.
L7 Site-specific capability negotiation Site manifest names capability negotiation, browser fallback, POST fallback, live GET fallback, and unsupported-operation response.

Machine-readable companion: /spec/agent-executability-matrix.json.

边界

Agent runtimes execute. UAIX records the reviewed communication, memory, trust, evidence, and handoff boundary. UAIX.org does not execute third-party actions, certify safety, certify truth, endorse implementations, or replace local authorization policy.

Agent Compatibility Records