Version localisee en cours de revue
La norme UAI-1 anglaise et les enregistrements JSON lisibles par machine restent autoritaires. Cette page localisee est une aide de lecture et ne doit pas etre traitee comme une traduction normative separee.
Ce que l’ensemble de schémas valide
L’ensemble de schémas transforme UAI-1 en cibles de validation publiées que les outils, les exécutions de CI et les ponts d’exécution peuvent appliquer de manière cohérente. La famille de schémas actuelle valide à la fois l’enveloppe partagée et les formes corporelles spécifiques au profil utilisées par le dossier public.
Enveloppe actuelle validée par machine
- Identité:version, profil, ID de message, source et cible.
- État du flux de travail:continuité de la conversation, mode de livraison, expiration, accusé de réception et références de tâches sélectionnées.
- Posture de confiance:canal, schéma d’authentification, principal, référence d’identification sélectionnée et conseils de fenêtre de relecture sélectionnés.
- Auditabilité:provenance, intégrité et métadonnées d’extension contrôlées.
Familles de schémas actuelles
uai.intent.request.v1valide l’intention, le sujet, les contraintes et les attentes de réponse côté demande.uai.intent.response.v1valide le statut côté résultat, le lien de demande, les notifications et le transfert de tâches sélectionnées.uai.capability.statement.v1valide les opérations, les profils, les points de terminaison et les schémas de sécurité de découverte.uai.error.v1valide les échecs publics typés avec le statut, le code, les détails et les sous-erreurs structurées.uai.conformance.result.v1valide les preuves de validateur et les références d’artefacts exportées.uai.task.status.v1valide la progression asynchrone, l’état, les références de résultats et les notes de mise à jour.
Ce que les schémas ne font pas seuls
Les schémas sont nécessaires mais pas suffisants. Le validateur applique toujours des contrôles de politique tels que l’expiration de la livraison, les conseils de référence de confiance, les références de tâches de réponse acceptée, la cohérence de la progression du statut des tâches et l’intégrité du résumé de conformité. Le document écrit porte toujours une intention sémantique et une signification de limite de support.
Catalogue de schémas publié
Utilisez le catalogue ci-dessous lorsque vous avez besoin des documents de schéma actuels exacts sur lesquels le validateur et les exemples sont construits.
Publication lisible par machine
Schemas UAI-1 publies
Ces enregistrements JSON Schema constituent le contrat destiné à l’implémentation pour les profils UAI-1 actuels, y compris les profils du modèle opérationnel de communication des agents. Ils couvrent la continuité de conversation, la sémantique de livraison, les métadonnées de confiance, l’état des tâches asynchrones, les erreurs typées, les preuves de résultat de conformité, l’identité de l’agent, les accusés de réception, les bloqueurs, les propositions de mémoire, les transmissions, les rapports finaux, les corrections et les règles de corps propres à chaque profil.
Ouvrir la collection JSON des schemas Ouvrir le JSON du registre des champs
Utilisez le catalogue des schemas avec le registre, la carte d ordre des champs, les exemples et le validateur avant de proposer une nouvelle variante d enveloppe.
Enregistrement de schema
UAI Intent Request v1
Schema for explicit intent requests in the richer UAI-1 public exchange envelope.
- Profil
- uai.intent.request.v1
- Spécification
- UAI-1
- Champs de corps requis
- intent, subject, requested_profile, parameters, constraints, response_profile
- Route
- /wp-json/uaix/v1/schemas/uai.intent.request.v1
Enregistrement de schema
UAI Intent Response v1
Schema for direct-result and accepted-task responses in the richer UAI-1 public exchange envelope.
- Profil
- uai.intent.response.v1
- Spécification
- UAI-1
- Champs de corps requis
- status, subject, request_message_id, result, notices
- Route
- /wp-json/uaix/v1/schemas/uai.intent.response.v1
Enregistrement de schema
UAI Capability Statement v1
Schema for discovery-facing capability, endpoint, security, async, and extension declarations in UAI-1.
- Profil
- uai.capability.statement.v1
- Spécification
- UAI-1
- Champs de corps requis
- capability_id, version, operations, input_profiles, output_profiles, async_profiles, security_schemes, endpoints
- Route
- /wp-json/uaix/v1/schemas/uai.capability.statement.v1
Enregistrement de schema
UAI Error v1
Schema for typed validation, transport, authorization, and execution errors in the richer UAI-1 envelope.
- Profil
- uai.error.v1
- Spécification
- UAI-1
- Champs de corps requis
- type, title, detail, status, code, retryable, instance
- Route
- /wp-json/uaix/v1/schemas/uai.error.v1
Enregistrement de schema
UAI Conformance Result v1
Schema for validator outputs, linked artifacts, and issue reports in the richer UAI-1 envelope.
- Profil
- uai.conformance.result.v1
- Spécification
- UAI-1
- Champs de corps requis
- status, checked_profile, issues, summary, artifacts
- Route
- /wp-json/uaix/v1/schemas/uai.conformance.result.v1
Enregistrement de schema
UAI Task Status v1
Schema for long-running async task state in the richer UAI-1 public exchange envelope.
- Profil
- uai.task.status.v1
- Spécification
- UAI-1
- Champs de corps requis
- task_id, state, subject, progress, status_message
- Route
- /wp-json/uaix/v1/schemas/uai.task.status.v1
Enregistrement de schema
UAI Agent Message v1
Portable multi-agent message packet for informational, directive, or query communication with context references and acknowledgement requirements. Uses the canonical UAI-1 envelope; agent runtimes execute and UAIX records the reviewed communication boundary.
- Profil
- uai.agent.message.v1
- Spécification
- UAI-1
- Champs de corps requis
- message_type, content, context_refs, requires_acknowledgement, intent_semantics, execution_constraints, support_boundary
- Route
- /wp-json/uaix/v1/schemas/uai.agent.message.v1
Enregistrement de schema
UAI Agent Acknowledgement v1
Acknowledgement packet that records receipt, parsing, validation, rejection, and acknowledgement-loop closure. Uses the canonical UAI-1 envelope; agent runtimes execute and UAIX records the reviewed communication boundary.
- Profil
- uai.agent.ack.v1
- Spécification
- UAI-1
- Champs de corps requis
- acknowledged_message_id, status, received_at_utc, closes_acknowledgement_loop, support_boundary
- Route
- /wp-json/uaix/v1/schemas/uai.agent.ack.v1
Enregistrement de schema
UAI Agent Task Status v1
Task status packet for progress, current action, UTC estimates, and correlation-linked task state from external runtimes. Uses the canonical UAI-1 envelope; agent runtimes execute and UAIX records the reviewed communication boundary.
- Profil
- uai.agent.task-status.v1
- Spécification
- UAI-1
- Champs de corps requis
- task_id, state, percent_complete, current_action, support_boundary
- Route
- /wp-json/uaix/v1/schemas/uai.agent.task-status.v1
Enregistrement de schema
UAI Agent Blocker v1
Blocker packet for authorization, resource, ambiguity, system fault, missing context, unsupported capability, validation, secret, destructive-action, and boundary conflicts. Uses the canonical UAI-1 envelope; agent runtimes execute and UAIX records the reviewed communication boundary.
- Profil
- uai.agent.blocker.v1
- Spécification
- UAI-1
- Champs de corps requis
- blocker_id, blocker_type, description, human_review_required, support_boundary
- Route
- /wp-json/uaix/v1/schemas/uai.agent.blocker.v1
Enregistrement de schema
UAI Agent Memory Proposal v1
Memory proposal packet that separates proposed durable facts from task execution and blocks secret or cold-memory direct promotion. Uses the canonical UAI-1 envelope; agent runtimes execute and UAIX records the reviewed communication boundary.
- Profil
- uai.agent.memory-proposal.v1
- Spécification
- UAI-1
- Champs de corps requis
- proposal_id, source_type, proposed_facts, proposed_status, task_execution_separation, support_boundary
- Route
- /wp-json/uaix/v1/schemas/uai.agent.memory-proposal.v1
Enregistrement de schema
UAI Agent Handoff v1
Handoff packet for transferring task responsibility with target actor, context summary, reason, and exact next action. Uses the canonical UAI-1 envelope; agent runtimes execute and UAIX records the reviewed communication boundary.
- Profil
- uai.agent.handoff.v1
- Spécification
- UAI-1
- Champs de corps requis
- task_id, target_agent_id, context_summary, handoff_reason, exact_next_action, support_boundary
- Route
- /wp-json/uaix/v1/schemas/uai.agent.handoff.v1
Enregistrement de schema
UAI Agent Final Report v1
Final report packet requiring complete task evidence, files, tests, skipped checks, blockers, risks, memory decisions, and exact next action. Uses the canonical UAI-1 envelope; agent runtimes execute and UAIX records the reviewed communication boundary.
- Profil
- uai.agent.final-report.v1
- Spécification
- UAI-1
- Champs de corps requis
- task_id, summary, files_changed, new_files, tests_run, skipped_checks, blockers, risks, validation_evidence, memory_updates_proposed, memory_updates_skipped, exact_next_action, support_boundary
- Route
- /wp-json/uaix/v1/schemas/uai.agent.final-report.v1
Enregistrement de schema
UAI Agent Correction v1
Correction packet that preserves immutable history by explaining what changed and why instead of deleting prior messages. Uses the canonical UAI-1 envelope; agent runtimes execute and UAIX records the reviewed communication boundary.
- Profil
- uai.agent.correction.v1
- Spécification
- UAI-1
- Champs de corps requis
- original_message_id, correction_reason, changed_summary, support_boundary
- Route
- /wp-json/uaix/v1/schemas/uai.agent.correction.v1
Enregistrement de schema
UAI Capability Profile v1
Capability-adaptive web interaction profile for declaring the client level, safe fallbacks, consent boundaries, known limits, and evidence expected before an agent or browser claims support.
- Profil
- uai.capability.profile.v1
- Spécification
- UAI-1
- Champs de corps requis
- client_level, client_name, can_fetch_static, can_fetch_json, can_execute_javascript, can_use_browser_ui, can_post_data, can_authenticate, can_call_tools, can_run_long_tasks, can_store_memory, can_coordinate_agents, requires_human_consent_for, recommended_uaix_profiles, fallback_behavior, known_limits, evidence_requirements, safe_default_response
- Route
- /wp-json/uaix/v1/schemas/uai.capability.profile.v1
Enregistrement de schema
UAI Capability Negotiation v1
Capability negotiation record for matching a task to the safest client level, unsupported features, consent boundary, fallback behavior, and evidence requirements.
- Profil
- uai.capability.negotiation.v1
- Spécification
- UAI-1
- Champs de corps requis
- negotiation_id, requested_client_level, observed_client_level, selected_client_level, selected_profile, requested_operation, unsupported_features, fallback_behavior, consent_boundaries, evidence_requirements, recommended_uaix_profiles, safe_default_response, support_boundary
- Route
- /wp-json/uaix/v1/schemas/uai.capability.negotiation.v1
Enregistrement de schema
UAI Limited Browser Client v1
L0 client capability profile for static text, static HTML, Markdown, sitemap, llms.txt, and JSON fetches without JavaScript execution or write authority.
- Profil
- uai.client.limited-browser.v1
- Spécification
- UAI-1
- Champs de corps requis
- client_level, client_name, can_fetch_static, can_fetch_json, can_execute_javascript, can_use_browser_ui, can_post_data, can_authenticate, can_call_tools, can_run_long_tasks, can_store_memory, can_coordinate_agents, requires_human_consent_for, recommended_uaix_profiles, fallback_behavior, known_limits, evidence_requirements, safe_default_response
- Route
- /wp-json/uaix/v1/schemas/uai.client.limited-browser.v1
Enregistrement de schema
UAI Structured Fetch Client v1
L1 client capability profile for predictable structured fetch of static resources and machine-readable JSON with low-token, no-JavaScript fallbacks.
- Profil
- uai.client.structured-fetch.v1
- Spécification
- UAI-1
- Champs de corps requis
- client_level, client_name, can_fetch_static, can_fetch_json, can_execute_javascript, can_use_browser_ui, can_post_data, can_authenticate, can_call_tools, can_run_long_tasks, can_store_memory, can_coordinate_agents, requires_human_consent_for, recommended_uaix_profiles, fallback_behavior, known_limits, evidence_requirements, safe_default_response
- Route
- /wp-json/uaix/v1/schemas/uai.client.structured-fetch.v1
Enregistrement de schema
UAI Browser-Assisted Client v1
L2 client capability profile for human-visible browser assistance, JavaScript rendering, and parity checks without autonomous tool execution.
- Profil
- uai.client.browser-assisted.v1
- Spécification
- UAI-1
- Champs de corps requis
- client_level, client_name, can_fetch_static, can_fetch_json, can_execute_javascript, can_use_browser_ui, can_post_data, can_authenticate, can_call_tools, can_run_long_tasks, can_store_memory, can_coordinate_agents, requires_human_consent_for, recommended_uaix_profiles, fallback_behavior, known_limits, evidence_requirements, safe_default_response
- Route
- /wp-json/uaix/v1/schemas/uai.client.browser-assisted.v1
Enregistrement de schema
UAI Tool Agent Client v1
L3 client capability profile for tool-calling agents that can fetch, authenticate, and post through explicit consent and idempotency controls.
- Profil
- uai.client.tool-agent.v1
- Spécification
- UAI-1
- Champs de corps requis
- client_level, client_name, can_fetch_static, can_fetch_json, can_execute_javascript, can_use_browser_ui, can_post_data, can_authenticate, can_call_tools, can_run_long_tasks, can_store_memory, can_coordinate_agents, requires_human_consent_for, recommended_uaix_profiles, fallback_behavior, known_limits, evidence_requirements, safe_default_response
- Route
- /wp-json/uaix/v1/schemas/uai.client.tool-agent.v1
Enregistrement de schema
UAI Workflow Agent Client v1
L4 client capability profile for long-running workflow agents that preserve correlation, task status, fallback, consent, and final-report evidence.
- Profil
- uai.client.workflow-agent.v1
- Spécification
- UAI-1
- Champs de corps requis
- client_level, client_name, can_fetch_static, can_fetch_json, can_execute_javascript, can_use_browser_ui, can_post_data, can_authenticate, can_call_tools, can_run_long_tasks, can_store_memory, can_coordinate_agents, requires_human_consent_for, recommended_uaix_profiles, fallback_behavior, known_limits, evidence_requirements, safe_default_response
- Route
- /wp-json/uaix/v1/schemas/uai.client.workflow-agent.v1
Enregistrement de schema
UAI Multi-Agent Runtime Client v1
L5 client capability profile for external multi-agent runtimes that coordinate agents while preserving UAIX as the record and evidence boundary, not the executor.
- Profil
- uai.client.multi-agent-runtime.v1
- Spécification
- UAI-1
- Champs de corps requis
- client_level, client_name, can_fetch_static, can_fetch_json, can_execute_javascript, can_use_browser_ui, can_post_data, can_authenticate, can_call_tools, can_run_long_tasks, can_store_memory, can_coordinate_agents, requires_human_consent_for, recommended_uaix_profiles, fallback_behavior, known_limits, evidence_requirements, safe_default_response
- Route
- /wp-json/uaix/v1/schemas/uai.client.multi-agent-runtime.v1
Enregistrement de schema
UAI Audited Agent System Client v1
L6 client capability profile for high-assurance agent systems that attach provenance, audit evidence, consent records, final reports, and fallback proof.
- Profil
- uai.client.audited-agent-system.v1
- Spécification
- UAI-1
- Champs de corps requis
- client_level, client_name, can_fetch_static, can_fetch_json, can_execute_javascript, can_use_browser_ui, can_post_data, can_authenticate, can_call_tools, can_run_long_tasks, can_store_memory, can_coordinate_agents, requires_human_consent_for, recommended_uaix_profiles, fallback_behavior, known_limits, evidence_requirements, safe_default_response
- Route
- /wp-json/uaix/v1/schemas/uai.client.audited-agent-system.v1
Enregistrement de schema
UAIX Ability Profile L6 v1
UAIX Ability Profile L6 v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.
- Profil
- uaix.ability-profile.v1
- Spécification
- UAI-1
- Champs de corps requis
- ability_profile_id, declared_level, label, capability_surface, authority_boundary, required_human_approval, no_op_triggers, evidence_requirements
- Route
- /wp-json/uaix/v1/schemas/uaix.ability-profile.v1
Enregistrement de schema
UAIX Startup Packet v1
UAIX Startup Packet v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.
- Profil
- uaix.startup-packet.v1
- Spécification
- UAI-1
- Champs de corps requis
- startup_packet_id, read_order, domain_boundaries, first_acceptable_response, no_op_triggers, validation_targets, identity, token_custody, discovery_bootstrap, safe_harbor, utc_requirements
- Route
- /wp-json/uaix/v1/schemas/uaix.startup-packet.v1
Enregistrement de schema
UAIX Memory Maintenance v1
Universal required UAIX memory package policy for memory lifecycle, hot/cold boundaries, compaction, archival policy, access controls, protected paths, validation behavior, and memory write safety.
- Profil
- uaix.memory-maintenance.v1
- Spécification
- UAI-1
- Champs de corps requis
- Route
- /wp-json/uaix/v1/schemas/uaix.memory-maintenance.v1
Enregistrement de schema
UAIX Next Recursive Prompt v1
Derived hot-memory resume artifact for code-bearing UAIX packages. Authoritative .uai records win on conflict. This record is not a second source of truth and does not authorize execution.
- Profil
- uaix.next-recursive-prompt.v1
- Spécification
- UAI-1
- Champs de corps requis
- Route
- /wp-json/uaix/v1/schemas/uaix.next-recursive-prompt.v1
Enregistrement de schema
UAIX Suspension Packet v1
UAIX Suspension Packet v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.
- Profil
- uaix.suspension-packet.v1
- Spécification
- UAI-1
- Champs de corps requis
- suspension_packet_id, state_summary, checks_run, checks_skipped, blockers, next_safe_step, network_obstruction, retry_policy, evidence_packet, human_escalation
- Route
- /wp-json/uaix/v1/schemas/uaix.suspension-packet.v1
Enregistrement de schema
UAIX Receiver Brief v1
UAIX Receiver Brief v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.
- Profil
- uaix.receiver-brief.v1
- Spécification
- UAI-1
- Champs de corps requis
- receiver_brief_id, read_order, first_acceptable_response, domain_boundaries, escalation_triggers, no_op_triggers
- Route
- /wp-json/uaix/v1/schemas/uaix.receiver-brief.v1
Enregistrement de schema
UAIX Memory Firewall Policy v1
UAIX Memory Firewall Policy v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.
- Profil
- uaix.memory-firewall-policy.v1
- Spécification
- UAI-1
- Champs de corps requis
- policy_id, quarantine_default, adoption_requirements, blocked_requests, no_op_triggers, human_review_required
- Route
- /wp-json/uaix/v1/schemas/uaix.memory-firewall-policy.v1
Enregistrement de schema
UAIX No-Op Trigger Catalog v1
UAIX No-Op Trigger Catalog v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.
- Profil
- uaix.no-op-trigger-catalog.v1
- Spécification
- UAI-1
- Champs de corps requis
- catalog_id, triggers, default_response, human_review_url, forbidden_recovery
- Route
- /wp-json/uaix/v1/schemas/uaix.no-op-trigger-catalog.v1
Enregistrement de schema
UAIX Authority Boundary v1
UAIX Authority Boundary v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.
- Profil
- uaix.authority-boundary.v1
- Spécification
- UAI-1
- Champs de corps requis
- matrix_id, boundaries, not_authorized_for, no_op_triggers, safe_quote_summary
- Route
- /wp-json/uaix/v1/schemas/uaix.authority-boundary.v1
Enregistrement de schema
UAIX Conformance Evidence v1
UAIX Conformance Evidence v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.
- Profil
- uaix.conformance-evidence.v1
- Spécification
- UAI-1
- Champs de corps requis
- evidence_id, profile_id, schema_url, fixture_url, checks, result, limitations
- Route
- /wp-json/uaix/v1/schemas/uaix.conformance-evidence.v1
Enregistrement de schema
UAIX Evaluation Packet Summary v1
UAIX Evaluation Packet Summary v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.
- Profil
- uaix.evaluation-packet-summary.v1
- Spécification
- UAI-1
- Champs de corps requis
- summary_id, packet_profiles, required_levels, no_op_triggers, limitations
- Route
- /wp-json/uaix/v1/schemas/uaix.evaluation-packet-summary.v1
Enregistrement de schema
UAIX Ability Profile L6 v1
UAIX Ability Profile L6 v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.
- Profil
- uaix.ability-profile.l0.v1
- Spécification
- UAI-1
- Champs de corps requis
- ability_profile_id, declared_level, label, capability_surface, authority_boundary, required_human_approval, no_op_triggers, evidence_requirements
- Route
- /wp-json/uaix/v1/schemas/uaix.ability-profile.l0.v1
Enregistrement de schema
UAIX Ability Profile L6 v1
UAIX Ability Profile L6 v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.
- Profil
- uaix.ability-profile.l1.v1
- Spécification
- UAI-1
- Champs de corps requis
- ability_profile_id, declared_level, label, capability_surface, authority_boundary, required_human_approval, no_op_triggers, evidence_requirements
- Route
- /wp-json/uaix/v1/schemas/uaix.ability-profile.l1.v1
Enregistrement de schema
UAIX Ability Profile L6 v1
UAIX Ability Profile L6 v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.
- Profil
- uaix.ability-profile.l2.v1
- Spécification
- UAI-1
- Champs de corps requis
- ability_profile_id, declared_level, label, capability_surface, authority_boundary, required_human_approval, no_op_triggers, evidence_requirements
- Route
- /wp-json/uaix/v1/schemas/uaix.ability-profile.l2.v1
Enregistrement de schema
UAIX Ability Profile L6 v1
UAIX Ability Profile L6 v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.
- Profil
- uaix.ability-profile.l3.v1
- Spécification
- UAI-1
- Champs de corps requis
- ability_profile_id, declared_level, label, capability_surface, authority_boundary, required_human_approval, no_op_triggers, evidence_requirements
- Route
- /wp-json/uaix/v1/schemas/uaix.ability-profile.l3.v1
Enregistrement de schema
UAIX Ability Profile L6 v1
UAIX Ability Profile L6 v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.
- Profil
- uaix.ability-profile.l4.v1
- Spécification
- UAI-1
- Champs de corps requis
- ability_profile_id, declared_level, label, capability_surface, authority_boundary, required_human_approval, no_op_triggers, evidence_requirements
- Route
- /wp-json/uaix/v1/schemas/uaix.ability-profile.l4.v1
Enregistrement de schema
UAIX Ability Profile L6 v1
UAIX Ability Profile L6 v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.
- Profil
- uaix.ability-profile.l5.v1
- Spécification
- UAI-1
- Champs de corps requis
- ability_profile_id, declared_level, label, capability_surface, authority_boundary, required_human_approval, no_op_triggers, evidence_requirements
- Route
- /wp-json/uaix/v1/schemas/uaix.ability-profile.l5.v1
Enregistrement de schema
UAIX Ability Profile L6 v1
UAIX Ability Profile L6 v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.
- Profil
- uaix.ability-profile.l6.v1
- Spécification
- UAI-1
- Champs de corps requis
- ability_profile_id, declared_level, label, capability_surface, authority_boundary, required_human_approval, no_op_triggers, evidence_requirements
- Route
- /wp-json/uaix/v1/schemas/uaix.ability-profile.l6.v1
Enregistrement de schema
UAIX Expression-Concept Review v1
UAIX Expression-Concept Review v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.
- Profil
- uaix.evaluation.expression-concept-review.v1
- Spécification
- UAI-1
- Champs de corps requis
- source_expression, concept_boundary, interpretation, confidence, no_op_triggers
- Route
- /wp-json/uaix/v1/schemas/uaix.evaluation.expression-concept-review.v1
Enregistrement de schema
UAIX Resource-Economy Trace v1
UAIX Resource-Economy Trace v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.
- Profil
- uaix.evaluation.resource-economy-trace.v1
- Spécification
- UAI-1
- Champs de corps requis
- resource_scope, cost_model, limits, evidence_refs, no_op_triggers
- Route
- /wp-json/uaix/v1/schemas/uaix.evaluation.resource-economy-trace.v1
Enregistrement de schema
UAIX Operator Decision v1
UAIX Operator Decision v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.
- Profil
- uaix.evaluation.operator-decision.v1
- Spécification
- UAI-1
- Champs de corps requis
- decision, authority_basis, options_reviewed, human_review_required, no_op_triggers
- Route
- /wp-json/uaix/v1/schemas/uaix.evaluation.operator-decision.v1
Enregistrement de schema
UAIX No-op Justification v1
UAIX No-op Justification v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.
- Profil
- uaix.evaluation.no-op-justification.v1
- Spécification
- UAI-1
- Champs de corps requis
- trigger, reason, missing_evidence, human_review_url, safe_next_step
- Route
- /wp-json/uaix/v1/schemas/uaix.evaluation.no-op-justification.v1
Enregistrement de schema
UAIX Local Sandbox Safety Review v1
UAIX Local Sandbox Safety Review v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.
- Profil
- uaix.evaluation.local-sandbox-safety-review.v1
- Spécification
- UAI-1
- Champs de corps requis
- sandbox_scope, unsafe_requests, blocked_operations, review_result, no_op_triggers
- Route
- /wp-json/uaix/v1/schemas/uaix.evaluation.local-sandbox-safety-review.v1
Enregistrement de schema
UAIX Memory Ecosystem Handoff v1
UAIX Memory Ecosystem Handoff v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.
- Profil
- uaix.evaluation.memory-ecosystem-handoff.v1
- Spécification
- UAI-1
- Champs de corps requis
- source_memory, quarantine_status, promotion_targets, conflicts, receiver_brief
- Route
- /wp-json/uaix/v1/schemas/uaix.evaluation.memory-ecosystem-handoff.v1
Enregistrement de schema
UAIX DE11 Benchmark Summary v1
UAIX DE11 Benchmark Summary v1 profile for UAI-1 review packets. UAIX records are schemas, profiles, handoff packets, and conformance evidence. They do not authorize execution, prove safety, validate credentials, or certify agent intelligence.
- Profil
- uaix.evaluation.de11-benchmark-summary.v1
- Spécification
- UAI-1
- Champs de corps requis
- benchmark_id, bounded_scope, reference_result, limitations, non_claims
- Route
- /wp-json/uaix/v1/schemas/uaix.evaluation.de11-benchmark-summary.v1
Enregistrement de schema
UAIX .uaix Package Manifest Draft v0.1
Manifest schema for the Draft v0.1 .uaix desktop AI memory package container. The package is local memory and evidence, not runtime authority.
- Profil
- uaix.package.v0.1
- Spécification
- UAI-1
- Champs de corps requis
- Route
- /wp-json/uaix/v1/schemas/uaix.package.v0.1
Enregistrement de schema
UAIX Persona v1
Scoped UAIX persona memory file for non-project assistant packages, bounded personality packages, and packages that support persona switching.
- Profil
- uaix.persona.v1
- Spécification
- UAI-1
- Champs de corps requis
- Route
- /wp-json/uaix/v1/schemas/uaix.persona.v1
Enregistrement de schema
UAIX SPEC-01 Canonical Envelope v1
Publication-envelope contract for portable evidence-bearing UAIX records, including payload, evidence, redaction, trust, signature status, verification, exceptions, and warnings. Uses the canonical UAI-1 transport envelope; UAIX records evidence and handoff boundaries but does not authorize execution.
- Profil
- uaix.spec-01.envelope.v1
- Spécification
- UAI-1
- Champs de corps requis
- uaixVersion, spec, envelopeId, createdUtc, issuer, issuerDisplayName, issuerPublicUrl, issuerCapabilityLevel, audience, lifecycleState, trustPosture, payloadType, payloadSchema, payload, evidence, redactions, signature, signatureStatus, verification, exceptions, warnings, rules, supportBoundary, localPolicyWins
- Route
- /wp-json/uaix/v1/schemas/uaix.spec-01.envelope.v1
Enregistrement de schema
UAIX Capability Profile v1
UAIX capability profile for declaring L0-L6 client posture, consent boundaries, fallback behavior, evidence requirements, and safe default behavior. Uses the canonical UAI-1 transport envelope; UAIX records evidence and handoff boundaries but does not authorize execution.
- Profil
- uaix.capability-profile.v1
- Spécification
- UAI-1
- Champs de corps requis
- capabilityProfileId, profileVersion, declaredLevel, supportedLevels, capabilities, consentRequiredFor, fallbacks, safeDefaultResponse, evidenceRequirements, supportBoundary, localPolicyWins
- Route
- /wp-json/uaix/v1/schemas/uaix.capability-profile.v1
Enregistrement de schema
UAIX Capability Ladder v1
Machine-readable L0-L6 capability ladder with safe fallbacks, unsupported implication boundaries, and reference-only client scenarios. Uses the canonical UAI-1 transport envelope; UAIX records evidence and handoff boundaries but does not authorize execution.
- Profil
- uaix.capability-ladder.v1
- Spécification
- UAI-1
- Champs de corps requis
- ladderId, levels, fallbackRules, safeDefaultResponse, referenceExamples, supportBoundary, localPolicyWins
- Route
- /wp-json/uaix/v1/schemas/uaix.capability-ladder.v1
Enregistrement de schema
UAIX SPEC-02 Project Handoff v1
Portable project memory and custody transfer contract for humans, agents, vendors, future sessions, and reviewed runtime consumers. Uses the canonical UAI-1 transport envelope; UAIX records evidence and handoff boundaries but does not authorize execution.
- Profil
- uaix.spec-02.project-handoff.v1
- Spécification
- UAI-1
- Champs de corps requis
- projectId, handoffId, createdUtc, owner, custodian, frontDoor, memoryRoots, requiredReads, currentState, constraints, decisions, nextActions, targetedChecks, evidence, redactions, warnings, referenceScenarios, supportBoundary, localPolicyWins
- Route
- /wp-json/uaix/v1/schemas/uaix.spec-02.project-handoff.v1
Enregistrement de schema
UAIX SPEC-03 AGENTS.md Metadata v1
AGENTS.md front-door metadata for canonical roots, nested instruction scope, command policy, memory loading, and safety boundaries. Uses the canonical UAI-1 transport envelope; UAIX records evidence and handoff boundaries but does not authorize execution.
- Profil
- uaix.spec-03.agents-md-metadata.v1
- Spécification
- UAI-1
- Champs de corps requis
- repositoryId, canonicalRoot, agentsMdPath, coordinatorPath, localUaiRoot, nestedScopes, requiredReads, commandPolicy, forbiddenOperations, memoryPolicy, securityBoundaries, examples, supportBoundary, localPolicyWins
- Route
- /wp-json/uaix/v1/schemas/uaix.spec-03.agents-md-metadata.v1
Enregistrement de schema
UAIX SPEC-04 File Handoff v1
Safe supplied-file intake contract for manifests, bucket review, disposition, redaction, evidence, lifecycle, blocked-file rules, and preservation after durable outcome. Uses the canonical UAI-1 transport envelope; UAIX records evidence and handoff boundaries but does not authorize execution.
- Profil
- uaix.spec-04.file-handoff.v1
- Spécification
- UAI-1
- Champs de corps requis
- handoffId, createdUtc, intakeBuckets, fileManifest, reviewDispositions, redactionPolicy, lifecycle, preservationPolicy, evidence, blockedFileRules, supportBoundary, localPolicyWins
- Route
- /wp-json/uaix/v1/schemas/uaix.spec-04.file-handoff.v1
Enregistrement de schema
UAIX Review Receipt v1
Review receipt for inspected UAIX envelopes, checks, skipped checks, warnings, exceptions, trust decision, and local-policy result. Uses the canonical UAI-1 transport envelope; UAIX records evidence and handoff boundaries but does not authorize execution.
- Profil
- uaix.review-receipt.v1
- Spécification
- UAI-1
- Champs de corps requis
- receiptId, reviewedEnvelopeId, reviewedUtc, reviewer, reviewResult, checksRun, checksSkipped, warnings, exceptions, trustDecision, supportBoundary, localPolicyWins
- Route
- /wp-json/uaix/v1/schemas/uaix.review-receipt.v1
Enregistrement de schema
UAIX Public-Safe Audit Digest v1
Public-safe audit digest for evidence references, redactions, public findings, excluded private material, verification, exceptions, and warnings. Uses the canonical UAI-1 transport envelope; UAIX records evidence and handoff boundaries but does not authorize execution.
- Profil
- uaix.public-safe-audit-digest.v1
- Spécification
- UAI-1
- Champs de corps requis
- digestId, subject, createdUtc, scope, evidenceRefs, redactions, publicFindings, privateMaterialExcluded, verification, exceptions, warnings, supportBoundary, localPolicyWins
- Route
- /wp-json/uaix/v1/schemas/uaix.public-safe-audit-digest.v1
Enregistrement de schema
UAIX Redaction Policy v1
Redaction policy for secret patterns, data classes, review gates, never-publish values, verification, exceptions, and warnings. Uses the canonical UAI-1 transport envelope; UAIX records evidence and handoff boundaries but does not authorize execution.
- Profil
- uaix.redaction-policy.v1
- Spécification
- UAI-1
- Champs de corps requis
- policyId, createdUtc, appliesTo, secretPatterns, dataClasses, redactionActions, reviewRequiredFor, neverPublish, verification, exceptions, warnings, supportBoundary, localPolicyWins
- Route
- /wp-json/uaix/v1/schemas/uaix.redaction-policy.v1
Registre de terrain publié
Le registre de terrain conserve l’enregistrement source JSON avec clé, l’ordre de transport sans clé et l’ordre de corps/composant imbriqué alignés dans tout le contrat public. Traitez-le comme faisant partie du dossier de sortie lisible par machine, et non comme une note de commodité sélectionnée.
Registre des champs
Registre public de l ordre des champs sans cles
Le registre des champs lisible par machine reste autoritaire. Cette aide localisee explique son role sans remplacer les enregistrements JSON publics.
Ordre de l enveloppe
Champs racine pour les enregistrements avec ou sans cles
uai_version: Declares the active UAI protocol release for the message.profile: Selects the exact published message profile.message_id: Stable message identifier used for review, tracing, and cross-record references.source: Describes the sender or producing system.target: Describes the intended receiving system, record, or audience.conversation: Carries conversation continuity, turn identity, and parent linkage.delivery: Carries sync versus async mode, priority, expiry, and acknowledgment expectations.trust: Declares trust-channel, authentication, credential, signature, replay-window, verifier, proof, and status hints.body: Profile-specific payload content.provenance: Carries trace, lineage, issued-at, and model or agent provenance details.integrity: Carries checksum, algorithm, and canonicalization information.extensions: Lists declared extension namespaces attached to the message.
Ordre des composants
Structures imbriquees qui restent stables entre profils
- source:
type, id, label, uri, did, role, implementation, project - target:
type, id, label, uri, did, role, implementation, project - conversation:
conversation_id, turn_id, parent_message_id, traceparent, sequence, correlation_id - delivery:
mode, priority, expires_at, reply_requested, ack_required, task_ref, idempotency_key, retry_count, sequence, lifecycle, timeout_ms, fallback_directive, expected_output_schema, duplicate_of_message_id, dedupe_behavior - trust:
channel, auth_scheme, principal, credential_ref, signature_ref, replay_window_id, trust_profile, verification_status, credential_status, verifier_ref, trust_root_ref, proof_ref, replay_policy_ref, verification_checked_at, verification_expires_at, assurance_level - provenance:
trace_id, parent_trace_id, issued_at, log_ref, agent_id, model_id, confidence, lineage - lineage_item:
stage, actor_id, model_id, note - integrity:
version, algorithm, canonicalization, checksum - extension_item:
namespace, purpose, critical - issue_item:
severity, code, message, path, help_url - error_detail_item:
path, code, message, schemaPointer, payloadPointer, field, expected, actual
Ordre de communication agent
Champs universels pour les paquets uai.agent.*
uai_version: Declares the active UAI protocol release for the agent communication packet.profile: Selects the exact published agent communication packet profile.message_id: Stable agent communication packet identifier used for review, tracing, and cross-record references.source: Describes the sender or producing system.target: Describes the intended receiving system, record, or audience.conversation: Carries conversation continuity, turn identity, and parent linkage.delivery: Carries sync versus async mode, priority, expiry, and acknowledgment expectations.trust: Declares trust-channel, authentication, credential, signature, replay-window, verifier, proof, and status hints.body: Profile-specific payload content.provenance: Carries trace, lineage, issued-at, and model or agent provenance details.integrity: Carries checksum, algorithm, and canonicalization information.extensions: Lists declared extension namespaces attached to the agent communication packet.
Ordre du corps
uai.intent.request.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
intent, subject, requested_profile, parameters, constraints, response_profile
Ordre du corps
uai.intent.response.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
status, subject, request_message_id, result, notices, task_ref
Ordre du corps
uai.capability.statement.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
capability_id, version, operations, input_profiles, output_profiles, async_profiles, security_schemes, transport_bindings, conformance_levels, error_codes, endpoints, extension_namespaces, implementation_tracks
Ordre du corps
uai.error.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
type, title, detail, status, code, retryable, instance, errors, next_step, uaixCode, uaixCategory, uaixSeverity, retryAfterUtc, retryAfterMs, rateLimit, blockedByPolicy, blockedByNetwork, bindingStatus, constraintViolation, schemaPointer, payloadPointer, field, line, column, expected, actual, allowedValues, documentationUrl, safeHarborUrl, supportReference, evidenceRefs, traceId, correlationId, evidenceRecommended, suspensionRecommended, redactionApplied
Ordre du corps
uai.conformance.result.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
status, checked_profile, issues, summary, artifacts, target_message_ref
Ordre du corps
uai.task.status.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
task_id, state, subject, progress, status_message, result_profile, result_ref, blocking_reasons, updated_fields
Ordre du corps
uai.agent.message.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
message_type, content, context_refs, requires_acknowledgement, intent_semantics, action_type, execution_constraints, support_boundary
Ordre du corps
uai.agent.ack.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
acknowledged_message_id, status, received_at_utc, rejection_reason, closes_acknowledgement_loop, support_boundary
Ordre du corps
uai.agent.task-status.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
task_id, state, percent_complete, current_action, estimated_completion_utc, support_boundary
Ordre du corps
uai.agent.blocker.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
blocker_id, blocker_type, description, human_review_required, proposed_resolution, support_boundary
Ordre du corps
uai.agent.memory-proposal.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
proposal_id, source_type, proposed_facts, proposed_status, task_execution_separation, review_required, support_boundary
Ordre du corps
uai.agent.handoff.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
task_id, target_agent_id, context_summary, handoff_reason, exact_next_action, delegated_authorization, support_boundary
Ordre du corps
uai.agent.final-report.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
task_id, summary, files_changed, new_files, tests_run, skipped_checks, blockers, risks, validation_evidence, memory_updates_proposed, memory_updates_skipped, exact_next_action, support_boundary
Ordre du corps
uai.agent.correction.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
original_message_id, correction_reason, changed_summary, corrected_fields, revised_payload, support_boundary
Ordre du corps
uai.capability.profile.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
client_level, client_name, can_fetch_static, can_fetch_json, can_execute_javascript, can_use_browser_ui, can_post_data, can_authenticate, can_call_tools, can_run_long_tasks, can_store_memory, can_coordinate_agents, requires_human_consent_for, recommended_uaix_profiles, fallback_behavior, known_limits, evidence_requirements, safe_default_response, support_boundary, carcinus_boundary, localendpoint_boundary
Ordre du corps
uai.capability.negotiation.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
negotiation_id, requested_client_level, observed_client_level, selected_client_level, selected_profile, requested_operation, unsupported_features, fallback_behavior, consent_boundaries, evidence_requirements, recommended_uaix_profiles, safe_default_response, support_boundary, carcinus_boundary, localendpoint_boundary
Ordre du corps
uai.client.limited-browser.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
client_level, client_name, can_fetch_static, can_fetch_json, can_execute_javascript, can_use_browser_ui, can_post_data, can_authenticate, can_call_tools, can_run_long_tasks, can_store_memory, can_coordinate_agents, requires_human_consent_for, recommended_uaix_profiles, fallback_behavior, known_limits, evidence_requirements, safe_default_response, support_boundary, carcinus_boundary, localendpoint_boundary
Ordre du corps
uai.client.structured-fetch.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
client_level, client_name, can_fetch_static, can_fetch_json, can_execute_javascript, can_use_browser_ui, can_post_data, can_authenticate, can_call_tools, can_run_long_tasks, can_store_memory, can_coordinate_agents, requires_human_consent_for, recommended_uaix_profiles, fallback_behavior, known_limits, evidence_requirements, safe_default_response, support_boundary, carcinus_boundary, localendpoint_boundary
Ordre du corps
uai.client.browser-assisted.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
client_level, client_name, can_fetch_static, can_fetch_json, can_execute_javascript, can_use_browser_ui, can_post_data, can_authenticate, can_call_tools, can_run_long_tasks, can_store_memory, can_coordinate_agents, requires_human_consent_for, recommended_uaix_profiles, fallback_behavior, known_limits, evidence_requirements, safe_default_response, support_boundary, carcinus_boundary, localendpoint_boundary
Ordre du corps
uai.client.tool-agent.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
client_level, client_name, can_fetch_static, can_fetch_json, can_execute_javascript, can_use_browser_ui, can_post_data, can_authenticate, can_call_tools, can_run_long_tasks, can_store_memory, can_coordinate_agents, requires_human_consent_for, recommended_uaix_profiles, fallback_behavior, known_limits, evidence_requirements, safe_default_response, support_boundary, carcinus_boundary, localendpoint_boundary
Ordre du corps
uai.client.workflow-agent.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
client_level, client_name, can_fetch_static, can_fetch_json, can_execute_javascript, can_use_browser_ui, can_post_data, can_authenticate, can_call_tools, can_run_long_tasks, can_store_memory, can_coordinate_agents, requires_human_consent_for, recommended_uaix_profiles, fallback_behavior, known_limits, evidence_requirements, safe_default_response, support_boundary, carcinus_boundary, localendpoint_boundary
Ordre du corps
uai.client.multi-agent-runtime.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
client_level, client_name, can_fetch_static, can_fetch_json, can_execute_javascript, can_use_browser_ui, can_post_data, can_authenticate, can_call_tools, can_run_long_tasks, can_store_memory, can_coordinate_agents, requires_human_consent_for, recommended_uaix_profiles, fallback_behavior, known_limits, evidence_requirements, safe_default_response, support_boundary, carcinus_boundary, localendpoint_boundary
Ordre du corps
uai.client.audited-agent-system.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
client_level, client_name, can_fetch_static, can_fetch_json, can_execute_javascript, can_use_browser_ui, can_post_data, can_authenticate, can_call_tools, can_run_long_tasks, can_store_memory, can_coordinate_agents, requires_human_consent_for, recommended_uaix_profiles, fallback_behavior, known_limits, evidence_requirements, safe_default_response, support_boundary, carcinus_boundary, localendpoint_boundary
Ordre du corps
uaix.ability-profile.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
ability_profile_id, declared_level, label, capability_surface, authority_boundary, required_human_approval, no_op_triggers, evidence_requirements
Ordre du corps
uaix.startup-packet.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
startup_packet_id, read_order, domain_boundaries, first_acceptable_response, no_op_triggers, validation_targets, identity, token_custody, discovery_bootstrap, safe_harbor, utc_requirements
Ordre du corps
uaix.memory-maintenance.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
uai_version, profile, schema_version, requirement, governance, protected_paths, validation, recommendation_boundary, provenance
Ordre du corps
uaix.next-recursive-prompt.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
uai_version, profile, schema_version, scope, lifecycle, activation_policy, objective, authoritative_refs, resume_context, next_loop, checks, writeback_policy, security, cold_memory, integrity, provenance
Ordre du corps
uaix.suspension-packet.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
suspension_packet_id, state_summary, checks_run, checks_skipped, blockers, next_safe_step, network_obstruction, retry_policy, evidence_packet, human_escalation
Ordre du corps
uaix.receiver-brief.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
receiver_brief_id, read_order, first_acceptable_response, domain_boundaries, escalation_triggers, no_op_triggers
Ordre du corps
uaix.memory-firewall-policy.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
policy_id, quarantine_default, adoption_requirements, blocked_requests, no_op_triggers, human_review_required
Ordre du corps
uaix.no-op-trigger-catalog.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
catalog_id, triggers, default_response, human_review_url, forbidden_recovery
Ordre du corps
uaix.authority-boundary.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
matrix_id, boundaries, not_authorized_for, no_op_triggers, safe_quote_summary
Ordre du corps
uaix.conformance-evidence.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
evidence_id, profile_id, schema_url, fixture_url, checks, result, limitations
Ordre du corps
uaix.evaluation-packet-summary.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
summary_id, packet_profiles, required_levels, no_op_triggers, limitations
Ordre du corps
uaix.ability-profile.l0.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
ability_profile_id, declared_level, label, capability_surface, authority_boundary, required_human_approval, no_op_triggers, evidence_requirements
Ordre du corps
uaix.ability-profile.l1.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
ability_profile_id, declared_level, label, capability_surface, authority_boundary, required_human_approval, no_op_triggers, evidence_requirements
Ordre du corps
uaix.ability-profile.l2.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
ability_profile_id, declared_level, label, capability_surface, authority_boundary, required_human_approval, no_op_triggers, evidence_requirements
Ordre du corps
uaix.ability-profile.l3.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
ability_profile_id, declared_level, label, capability_surface, authority_boundary, required_human_approval, no_op_triggers, evidence_requirements
Ordre du corps
uaix.ability-profile.l4.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
ability_profile_id, declared_level, label, capability_surface, authority_boundary, required_human_approval, no_op_triggers, evidence_requirements
Ordre du corps
uaix.ability-profile.l5.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
ability_profile_id, declared_level, label, capability_surface, authority_boundary, required_human_approval, no_op_triggers, evidence_requirements
Ordre du corps
uaix.ability-profile.l6.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
ability_profile_id, declared_level, label, capability_surface, authority_boundary, required_human_approval, no_op_triggers, evidence_requirements
Ordre du corps
uaix.evaluation.expression-concept-review.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
source_expression, concept_boundary, interpretation, confidence, no_op_triggers
Ordre du corps
uaix.evaluation.resource-economy-trace.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
resource_scope, cost_model, limits, evidence_refs, no_op_triggers
Ordre du corps
uaix.evaluation.operator-decision.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
decision, authority_basis, options_reviewed, human_review_required, no_op_triggers
Ordre du corps
uaix.evaluation.no-op-justification.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
trigger, reason, missing_evidence, human_review_url, safe_next_step
Ordre du corps
uaix.evaluation.local-sandbox-safety-review.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
sandbox_scope, unsafe_requests, blocked_operations, review_result, no_op_triggers
Ordre du corps
uaix.evaluation.memory-ecosystem-handoff.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
source_memory, quarantine_status, promotion_targets, conflicts, receiver_brief
Ordre du corps
uaix.evaluation.de11-benchmark-summary.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
benchmark_id, bounded_scope, reference_result, limitations, non_claims
Ordre du corps
uaix.package.v0.1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
uaixVersion, packageFormat, packageId, profileId, status, createdUtc, issuer, declaredScopes, entrypoints, files, integrity, supportBoundary
Ordre du corps
uaix.persona.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
uai_version, profile, schema_version, requirement, persona, preservation, boundaries, switching, provenance
Ordre du corps
uaix.spec-01.envelope.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
uaixVersion, spec, envelopeId, createdUtc, issuer, issuerDisplayName, issuerPublicUrl, issuerCapabilityLevel, audience, lifecycleState, trustPosture, payloadType, payloadSchema, payload, evidence, redactions, signature, signatureStatus, verification, exceptions, warnings, rules, supportBoundary, localPolicyWins
Ordre du corps
uaix.capability-profile.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
capabilityProfileId, profileVersion, declaredLevel, supportedLevels, capabilities, consentRequiredFor, fallbacks, safeDefaultResponse, evidenceRequirements, supportBoundary, localPolicyWins
Ordre du corps
uaix.capability-ladder.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
ladderId, levels, fallbackRules, safeDefaultResponse, referenceExamples, supportBoundary, localPolicyWins
Ordre du corps
uaix.spec-02.project-handoff.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
projectId, handoffId, createdUtc, owner, custodian, frontDoor, memoryRoots, requiredReads, currentState, constraints, decisions, nextActions, targetedChecks, evidence, redactions, warnings, referenceScenarios, supportBoundary, localPolicyWins
Ordre du corps
uaix.spec-03.agents-md-metadata.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
repositoryId, canonicalRoot, agentsMdPath, coordinatorPath, localUaiRoot, nestedScopes, requiredReads, commandPolicy, forbiddenOperations, memoryPolicy, securityBoundaries, examples, supportBoundary, localPolicyWins
Ordre du corps
uaix.spec-04.file-handoff.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
handoffId, createdUtc, intakeBuckets, fileManifest, reviewDispositions, redactionPolicy, lifecycle, preservationPolicy, evidence, blockedFileRules, supportBoundary, localPolicyWins
Ordre du corps
uaix.review-receipt.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
receiptId, reviewedEnvelopeId, reviewedUtc, reviewer, reviewResult, checksRun, checksSkipped, warnings, exceptions, trustDecision, supportBoundary, localPolicyWins
Ordre du corps
uaix.public-safe-audit-digest.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
digestId, subject, createdUtc, scope, evidenceRefs, redactions, publicFindings, privateMaterialExcluded, verification, exceptions, warnings, supportBoundary, localPolicyWins
Ordre du corps
uaix.redaction-policy.v1
Utilisez cette liste ordonnee lorsqu un transport choisit la forme optimisee sans cles plutot que le JSON lisible avec cles.
policyId, createdUtc, appliesTo, secretPatterns, dataClasses, redactionActions, reviewRequiredFor, neverPublish, verification, exceptions, warnings, supportBoundary, localPolicyWins
Comment utiliser cette rubrique
- Choisissez le profil que vous souhaitez prendre en charge et résolvez son schéma.
- Vérifiez la correspondanceRegistrel’entrée et le publicregistre de terrainavant de mettre en œuvre des hypothèses de transport compact ou d’ordre des corps.
- Exécutez leValidateuravec une publicationExempleou le message du candidat et conservez le résultat avec la preuve de libération.
- Effectuez toute modification liée à la version dansImplémentations, leJournal des changements, etRéférences et contributeurs.
Étape suivante
Continuez àRegistrepour la carte de profil stable, les indices de compatibilité et les liens schéma-exemple derrière la version actuelle.