What the schema set validates
The schema set turns UAI-1 into published validation targets that tools, CI runs, and runtime bridges can apply consistently. The current schema family validates both the shared envelope and the profile-specific body shapes used by the public record.
当前 machine-validated envelope
- 身份: version, profile, message ID, source, and target.
- Workflow state: conversation continuity, delivery mode, expiry, acknowledgement, and selected task references.
- 信任 posture: channel, auth scheme, principal, selected credential reference, and selected replay-window hints.
- Auditability: provenance, integrity, and controlled extension metadata.
当前 schema families
uai.intent.request.v1validates request-side intent, subject, constraints, and response expectations.uai.intent.response.v1validates result-side status, request linkage, notices, and selected task handoff.uai.capability.statement.v1validates discovery-facing operations, profiles, endpoints, and security schemes.uai.error.v1validates typed public failures with status, code, detail, and structured sub-errors.uai.conformance.result.v1validates exported validator evidence and artifact references.uai.task.status.v1validates async progress, state, result references, and update notes.
What the schemas do not do alone
模式 are necessary but not sufficient. The validator still applies policy checks such as delivery expiry, trust-reference hints, accepted-response task references, task-status progress consistency, and conformance-summary integrity. The written record still carries semantic intent and support-boundary meaning.
Published schema catalog
Use the catalog below when you need the exact current schema documents that the validator and examples are built against.
机器可读发布
已发布的 UAI-1 模式
These JSON 模式记录s are the implementation-facing contract for the current UAI-1 profiles, including the Agent Communication Operating Model profiles. They cover conversation continuity, delivery semantics, trust metadata, async task state, typed errors, conformance-result evidence, agent identity, acknowledgement, blockers, memory proposals, handoff, final reports, corrections, and profile-specific body rules.
Use the schema catalog with the registry, field-order map, examples, and validator route before inventing a new envelope variant.
模式记录
UAI 意图请求 v1
用于更丰富的 UAI-1 公共交换信封中显式意图请求的模式。
- 配置文件
- uai.intent.request.v1
- 规范
- UAI-1
- 必需正文字段
- intent, subject, requested_profile, parameters, constraints, response_profile
- 路由
- /wp-json/uaix/v1/schemas/uai.intent.request.v1
模式记录
UAI 意图响应 v1
用于更丰富的 UAI-1 公共交换信封中直接结果和已接受任务响应的模式。
- 配置文件
- uai.intent.response.v1
- 规范
- UAI-1
- 必需正文字段
- status, subject, request_message_id, result, notices
- 路由
- /wp-json/uaix/v1/schemas/uai.intent.response.v1
模式记录
UAI 能力声明 v1
用于 UAI-1 中面向发现的能力、端点、安全性、异步和扩展声明的模式。
- 配置文件
- uai.capability.statement.v1
- 规范
- UAI-1
- 必需正文字段
- capability_id, version, operations, input_profiles, output_profiles, async_profiles, security_schemes, endpoints
- 路由
- /wp-json/uaix/v1/schemas/uai.capability.statement.v1
模式记录
UAI 错误 v1
用于更丰富的 UAI-1 信封中类型化验证、传输、授权和执行错误的模式。
- 配置文件
- uai.error.v1
- 规范
- UAI-1
- 必需正文字段
- type, title, detail, status, code, retryable, instance
- 路由
- /wp-json/uaix/v1/schemas/uai.error.v1
模式记录
UAI 一致性结果 v1
用于更丰富的 UAI-1 信封中验证器输出、关联制品和问题报告的模式。
- 配置文件
- uai.conformance.result.v1
- 规范
- UAI-1
- 必需正文字段
- status, checked_profile, issues, summary, artifacts
- 路由
- /wp-json/uaix/v1/schemas/uai.conformance.result.v1
模式记录
UAI 任务状态 v1
用于更丰富的 UAI-1 公共交换信封中长时异步任务状态的模式。
- 配置文件
- uai.task.status.v1
- 规范
- UAI-1
- 必需正文字段
- task_id, state, subject, progress, status_message
- 路由
- /wp-json/uaix/v1/schemas/uai.task.status.v1
模式记录
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.
- 配置文件
- uai.agent.message.v1
- 规范
- UAI-1
- 必需正文字段
- message_type, content, context_refs, requires_acknowledgement, intent_semantics, execution_constraints, support_boundary
- 路由
- /wp-json/uaix/v1/schemas/uai.agent.message.v1
模式记录
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.
- 配置文件
- uai.agent.ack.v1
- 规范
- UAI-1
- 必需正文字段
- acknowledged_message_id, status, received_at_utc, closes_acknowledgement_loop, support_boundary
- 路由
- /wp-json/uaix/v1/schemas/uai.agent.ack.v1
模式记录
UAI Agent Task 状态 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.
- 配置文件
- uai.agent.task-status.v1
- 规范
- UAI-1
- 必需正文字段
- task_id, state, percent_complete, current_action, support_boundary
- 路由
- /wp-json/uaix/v1/schemas/uai.agent.task-status.v1
模式记录
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.
- 配置文件
- uai.agent.blocker.v1
- 规范
- UAI-1
- 必需正文字段
- blocker_id, blocker_type, description, human_review_required, support_boundary
- 路由
- /wp-json/uaix/v1/schemas/uai.agent.blocker.v1
模式记录
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.
- 配置文件
- uai.agent.memory-proposal.v1
- 规范
- UAI-1
- 必需正文字段
- proposal_id, source_type, proposed_facts, proposed_status, task_execution_separation, support_boundary
- 路由
- /wp-json/uaix/v1/schemas/uai.agent.memory-proposal.v1
模式记录
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.
- 配置文件
- uai.agent.handoff.v1
- 规范
- UAI-1
- 必需正文字段
- task_id, target_agent_id, context_summary, handoff_reason, exact_next_action, support_boundary
- 路由
- /wp-json/uaix/v1/schemas/uai.agent.handoff.v1
模式记录
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.
- 配置文件
- uai.agent.final-report.v1
- 规范
- UAI-1
- 必需正文字段
- 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
- 路由
- /wp-json/uaix/v1/schemas/uai.agent.final-report.v1
模式记录
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.
- 配置文件
- uai.agent.correction.v1
- 规范
- UAI-1
- 必需正文字段
- original_message_id, correction_reason, changed_summary, support_boundary
- 路由
- /wp-json/uaix/v1/schemas/uai.agent.correction.v1
模式记录
UAI Capability 配置文件 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.
- 配置文件
- uai.capability.profile.v1
- 规范
- UAI-1
- 必需正文字段
- 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
- 路由
- /wp-json/uaix/v1/schemas/uai.capability.profile.v1
模式记录
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.
- 配置文件
- uai.capability.negotiation.v1
- 规范
- UAI-1
- 必需正文字段
- 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
- 路由
- /wp-json/uaix/v1/schemas/uai.capability.negotiation.v1
模式记录
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.
- 配置文件
- uai.client.limited-browser.v1
- 规范
- UAI-1
- 必需正文字段
- 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
- 路由
- /wp-json/uaix/v1/schemas/uai.client.limited-browser.v1
模式记录
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.
- 配置文件
- uai.client.structured-fetch.v1
- 规范
- UAI-1
- 必需正文字段
- 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
- 路由
- /wp-json/uaix/v1/schemas/uai.client.structured-fetch.v1
模式记录
UAI Browser-Assisted Client v1
L2 client capability profile for human-visible browser assistance, JavaScript rendering, and parity checks without autonomous tool execution.
- 配置文件
- uai.client.browser-assisted.v1
- 规范
- UAI-1
- 必需正文字段
- 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
- 路由
- /wp-json/uaix/v1/schemas/uai.client.browser-assisted.v1
模式记录
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.
- 配置文件
- uai.client.tool-agent.v1
- 规范
- UAI-1
- 必需正文字段
- 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
- 路由
- /wp-json/uaix/v1/schemas/uai.client.tool-agent.v1
模式记录
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.
- 配置文件
- uai.client.workflow-agent.v1
- 规范
- UAI-1
- 必需正文字段
- 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
- 路由
- /wp-json/uaix/v1/schemas/uai.client.workflow-agent.v1
模式记录
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.
- 配置文件
- uai.client.multi-agent-runtime.v1
- 规范
- UAI-1
- 必需正文字段
- 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
- 路由
- /wp-json/uaix/v1/schemas/uai.client.multi-agent-runtime.v1
模式记录
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.
- 配置文件
- uai.client.audited-agent-system.v1
- 规范
- UAI-1
- 必需正文字段
- 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
- 路由
- /wp-json/uaix/v1/schemas/uai.client.audited-agent-system.v1
模式记录
UAIX Ability 配置文件 L6 v1
UAIX Ability 配置文件 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.
- 配置文件
- uaix.ability-profile.v1
- 规范
- UAI-1
- 必需正文字段
- ability_profile_id, declared_level, label, capability_surface, authority_boundary, required_human_approval, no_op_triggers, evidence_requirements
- 路由
- /wp-json/uaix/v1/schemas/uaix.ability-profile.v1
模式记录
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.
- 配置文件
- uaix.startup-packet.v1
- 规范
- UAI-1
- 必需正文字段
- startup_packet_id, read_order, domain_boundaries, first_acceptable_response, no_op_triggers, validation_targets, identity, token_custody, discovery_bootstrap, safe_harbor, utc_requirements
- 路由
- /wp-json/uaix/v1/schemas/uaix.startup-packet.v1
模式记录
UAIX Memory Maintenance v1
通用 required UAIX memory package policy for memory lifecycle, hot/cold boundaries, compaction, archival policy, access controls, protected paths, validation behavior, and memory write safety.
- 配置文件
- uaix.memory-maintenance.v1
- 规范
- UAI-1
- 必需正文字段
- 路由
- /wp-json/uaix/v1/schemas/uaix.memory-maintenance.v1
模式记录
UAIX 下一步 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.
- 配置文件
- uaix.next-recursive-prompt.v1
- 规范
- UAI-1
- 必需正文字段
- 路由
- /wp-json/uaix/v1/schemas/uaix.next-recursive-prompt.v1
模式记录
UAIX 暂停 Packet v1
UAIX 暂停 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.
- 配置文件
- uaix.suspension-packet.v1
- 规范
- UAI-1
- 必需正文字段
- suspension_packet_id, state_summary, checks_run, checks_skipped, blockers, next_safe_step, network_obstruction, retry_policy, evidence_packet, human_escalation
- 路由
- /wp-json/uaix/v1/schemas/uaix.suspension-packet.v1
模式记录
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.
- 配置文件
- uaix.receiver-brief.v1
- 规范
- UAI-1
- 必需正文字段
- receiver_brief_id, read_order, first_acceptable_response, domain_boundaries, escalation_triggers, no_op_triggers
- 路由
- /wp-json/uaix/v1/schemas/uaix.receiver-brief.v1
模式记录
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.
- 配置文件
- uaix.memory-firewall-policy.v1
- 规范
- UAI-1
- 必需正文字段
- policy_id, quarantine_default, adoption_requirements, blocked_requests, no_op_triggers, human_review_required
- 路由
- /wp-json/uaix/v1/schemas/uaix.memory-firewall-policy.v1
模式记录
UAIX No-Op Trigger 目录 v1
UAIX No-Op Trigger 目录 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.
- 配置文件
- uaix.no-op-trigger-catalog.v1
- 规范
- UAI-1
- 必需正文字段
- catalog_id, triggers, default_response, human_review_url, forbidden_recovery
- 路由
- /wp-json/uaix/v1/schemas/uaix.no-op-trigger-catalog.v1
模式记录
UAIX Authority 边界 v1
UAIX Authority 边界 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.
- 配置文件
- uaix.authority-boundary.v1
- 规范
- UAI-1
- 必需正文字段
- matrix_id, boundaries, not_authorized_for, no_op_triggers, safe_quote_summary
- 路由
- /wp-json/uaix/v1/schemas/uaix.authority-boundary.v1
模式记录
UAIX 一致性 证据 v1
UAIX 一致性 证据 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.
- 配置文件
- uaix.conformance-evidence.v1
- 规范
- UAI-1
- 必需正文字段
- evidence_id, profile_id, schema_url, fixture_url, checks, result, limitations
- 路由
- /wp-json/uaix/v1/schemas/uaix.conformance-evidence.v1
模式记录
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.
- 配置文件
- uaix.evaluation-packet-summary.v1
- 规范
- UAI-1
- 必需正文字段
- summary_id, packet_profiles, required_levels, no_op_triggers, limitations
- 路由
- /wp-json/uaix/v1/schemas/uaix.evaluation-packet-summary.v1
模式记录
UAIX Ability 配置文件 L6 v1
UAIX Ability 配置文件 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.
- 配置文件
- uaix.ability-profile.l0.v1
- 规范
- UAI-1
- 必需正文字段
- ability_profile_id, declared_level, label, capability_surface, authority_boundary, required_human_approval, no_op_triggers, evidence_requirements
- 路由
- /wp-json/uaix/v1/schemas/uaix.ability-profile.l0.v1
模式记录
UAIX Ability 配置文件 L6 v1
UAIX Ability 配置文件 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.
- 配置文件
- uaix.ability-profile.l1.v1
- 规范
- UAI-1
- 必需正文字段
- ability_profile_id, declared_level, label, capability_surface, authority_boundary, required_human_approval, no_op_triggers, evidence_requirements
- 路由
- /wp-json/uaix/v1/schemas/uaix.ability-profile.l1.v1
模式记录
UAIX Ability 配置文件 L6 v1
UAIX Ability 配置文件 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.
- 配置文件
- uaix.ability-profile.l2.v1
- 规范
- UAI-1
- 必需正文字段
- ability_profile_id, declared_level, label, capability_surface, authority_boundary, required_human_approval, no_op_triggers, evidence_requirements
- 路由
- /wp-json/uaix/v1/schemas/uaix.ability-profile.l2.v1
模式记录
UAIX Ability 配置文件 L6 v1
UAIX Ability 配置文件 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.
- 配置文件
- uaix.ability-profile.l3.v1
- 规范
- UAI-1
- 必需正文字段
- ability_profile_id, declared_level, label, capability_surface, authority_boundary, required_human_approval, no_op_triggers, evidence_requirements
- 路由
- /wp-json/uaix/v1/schemas/uaix.ability-profile.l3.v1
模式记录
UAIX Ability 配置文件 L6 v1
UAIX Ability 配置文件 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.
- 配置文件
- uaix.ability-profile.l4.v1
- 规范
- UAI-1
- 必需正文字段
- ability_profile_id, declared_level, label, capability_surface, authority_boundary, required_human_approval, no_op_triggers, evidence_requirements
- 路由
- /wp-json/uaix/v1/schemas/uaix.ability-profile.l4.v1
模式记录
UAIX Ability 配置文件 L6 v1
UAIX Ability 配置文件 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.
- 配置文件
- uaix.ability-profile.l5.v1
- 规范
- UAI-1
- 必需正文字段
- ability_profile_id, declared_level, label, capability_surface, authority_boundary, required_human_approval, no_op_triggers, evidence_requirements
- 路由
- /wp-json/uaix/v1/schemas/uaix.ability-profile.l5.v1
模式记录
UAIX Ability 配置文件 L6 v1
UAIX Ability 配置文件 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.
- 配置文件
- uaix.ability-profile.l6.v1
- 规范
- UAI-1
- 必需正文字段
- ability_profile_id, declared_level, label, capability_surface, authority_boundary, required_human_approval, no_op_triggers, evidence_requirements
- 路由
- /wp-json/uaix/v1/schemas/uaix.ability-profile.l6.v1
模式记录
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.
- 配置文件
- uaix.evaluation.expression-concept-review.v1
- 规范
- UAI-1
- 必需正文字段
- source_expression, concept_boundary, interpretation, confidence, no_op_triggers
- 路由
- /wp-json/uaix/v1/schemas/uaix.evaluation.expression-concept-review.v1
模式记录
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.
- 配置文件
- uaix.evaluation.resource-economy-trace.v1
- 规范
- UAI-1
- 必需正文字段
- resource_scope, cost_model, limits, evidence_refs, no_op_triggers
- 路由
- /wp-json/uaix/v1/schemas/uaix.evaluation.resource-economy-trace.v1
模式记录
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.
- 配置文件
- uaix.evaluation.operator-decision.v1
- 规范
- UAI-1
- 必需正文字段
- decision, authority_basis, options_reviewed, human_review_required, no_op_triggers
- 路由
- /wp-json/uaix/v1/schemas/uaix.evaluation.operator-decision.v1
模式记录
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.
- 配置文件
- uaix.evaluation.no-op-justification.v1
- 规范
- UAI-1
- 必需正文字段
- trigger, reason, missing_evidence, human_review_url, safe_next_step
- 路由
- /wp-json/uaix/v1/schemas/uaix.evaluation.no-op-justification.v1
模式记录
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.
- 配置文件
- uaix.evaluation.local-sandbox-safety-review.v1
- 规范
- UAI-1
- 必需正文字段
- sandbox_scope, unsafe_requests, blocked_operations, review_result, no_op_triggers
- 路由
- /wp-json/uaix/v1/schemas/uaix.evaluation.local-sandbox-safety-review.v1
模式记录
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.
- 配置文件
- uaix.evaluation.memory-ecosystem-handoff.v1
- 规范
- UAI-1
- 必需正文字段
- source_memory, quarantine_status, promotion_targets, conflicts, receiver_brief
- 路由
- /wp-json/uaix/v1/schemas/uaix.evaluation.memory-ecosystem-handoff.v1
模式记录
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.
- 配置文件
- uaix.evaluation.de11-benchmark-summary.v1
- 规范
- UAI-1
- 必需正文字段
- benchmark_id, bounded_scope, reference_result, limitations, non_claims
- 路由
- /wp-json/uaix/v1/schemas/uaix.evaluation.de11-benchmark-summary.v1
模式记录
UAIX SPEC-01 Canonical 信封 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 记录证据 and handoff boundaries but does not authorize execution.
- 配置文件
- uaix.spec-01.envelope.v1
- 规范
- UAI-1
- 必需正文字段
- uaixVersion, spec, envelopeId, createdUtc, issuer, issuerDisplayName, issuerPublicUrl, issuerCapabilityLevel, audience, lifecycleState, trustPosture, payloadType, payload模式, payload, evidence, redactions, signature, signature状态, verification, exceptions, warnings, rules, support边界, localPolicyWins
- 路由
- /wp-json/uaix/v1/schemas/uaix.spec-01.envelope.v1
模式记录
UAIX Capability 配置文件 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 记录证据 and handoff boundaries but does not authorize execution.
- 配置文件
- uaix.capability-profile.v1
- 规范
- UAI-1
- 必需正文字段
- capability配置文件Id, profileVersion, declaredLevel, supportedLevels, capabilities, consentRequiredFor, fallbacks, safe默认Response, evidenceRequirements, support边界, localPolicyWins
- 路由
- /wp-json/uaix/v1/schemas/uaix.capability-profile.v1
模式记录
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 记录证据 and handoff boundaries but does not authorize execution.
- 配置文件
- uaix.capability-ladder.v1
- 规范
- UAI-1
- 必需正文字段
- ladderId, levels, fallbackRules, safe默认Response, reference示例, support边界, localPolicyWins
- 路由
- /wp-json/uaix/v1/schemas/uaix.capability-ladder.v1
模式记录
UAIX SPEC-02 项目交接 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 记录证据 and handoff boundaries but does not authorize execution.
- 配置文件
- uaix.spec-02.project-handoff.v1
- 规范
- UAI-1
- 必需正文字段
- projectId, handoffId, createdUtc, owner, custodian, frontDoor, memoryRoots, requiredReads, currentState, constraints, decisions, nextActions, targeted检查s, evidence, redactions, warnings, reference场景s, support边界, localPolicyWins
- 路由
- /wp-json/uaix/v1/schemas/uaix.spec-02.project-handoff.v1
模式记录
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 记录证据 and handoff boundaries but does not authorize execution.
- 配置文件
- uaix.spec-03.agents-md-metadata.v1
- 规范
- UAI-1
- 必需正文字段
- repositoryId, canonicalRoot, agentsMdPath, coordinatorPath, localUaiRoot, nestedScopes, requiredReads, commandPolicy, forbiddenOperations, memoryPolicy, securityBoundaries, examples, support边界, localPolicyWins
- 路由
- /wp-json/uaix/v1/schemas/uaix.spec-03.agents-md-metadata.v1
模式记录
UAIX SPEC-04 文件交接 v1
Safe supplied-file intake contract for manifests, bucket review, disposition, redaction, evidence, lifecycle, blocked-file rules, and archives. Uses the canonical UAI-1 transport envelope; UAIX 记录证据 and handoff boundaries but does not authorize execution.
- 配置文件
- uaix.spec-04.file-handoff.v1
- 规范
- UAI-1
- 必需正文字段
- handoffId, createdUtc, intakeBuckets, fileManifest, reviewDispositions, redactionPolicy, lifecycle, archivePolicy, evidence, blockedFileRules, support边界, localPolicyWins
- 路由
- /wp-json/uaix/v1/schemas/uaix.spec-04.file-handoff.v1
模式记录
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 记录证据 and handoff boundaries but does not authorize execution.
- 配置文件
- uaix.review-receipt.v1
- 规范
- UAI-1
- 必需正文字段
- receiptId, reviewed信封Id, reviewedUtc, reviewer, reviewResult, checksRun, checksSkipped, warnings, exceptions, trustDecision, support边界, localPolicyWins
- 路由
- /wp-json/uaix/v1/schemas/uaix.review-receipt.v1
模式记录
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 记录证据 and handoff boundaries but does not authorize execution.
- 配置文件
- uaix.public-safe-audit-digest.v1
- 规范
- UAI-1
- 必需正文字段
- digestId, subject, createdUtc, scope, evidenceRefs, redactions, publicFindings, privateMaterialExcluded, verification, exceptions, warnings, support边界, localPolicyWins
- 路由
- /wp-json/uaix/v1/schemas/uaix.public-safe-audit-digest.v1
模式记录
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 记录证据 and handoff boundaries but does not authorize execution.
- 配置文件
- uaix.redaction-policy.v1
- 规范
- UAI-1
- 必需正文字段
- policyId, createdUtc, appliesTo, secret模式s, dataClasses, redactionActions, reviewRequiredFor, neverPublish, verification, exceptions, warnings, support边界, localPolicyWins
- 路由
- /wp-json/uaix/v1/schemas/uaix.redaction-policy.v1
Published field registry
The field registry keeps the keyed JSON source record, the keyless transport order, and the nested body/component order aligned across the public contract. Treat it as part of the machine-readable release record, not as a selected convenience note.
信封顺序
有键与无键记录的根字段
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: 配置文件-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.
组件顺序
跨配置文件保持稳定的嵌套结构
- 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
Agent communication order
通用 fields for uai.agent.* packets
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: 配置文件-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.
intent, subject, requested_profile, parameters, constraints, response_profile
status, subject, request_message_id, result, notices, task_ref
capability_id, version, operations, input_profiles, output_profiles, async_profiles, security_schemes, transport_bindings, conformance_levels, error_codes, endpoints, extension_namespaces, implementation_tracks
type, title, detail, status, code, retryable, instance, errors, next_step, uaixCode, uaixCategory, uaixSeverity, retryAfterUtc, retryAfterMs, rateLimit, blockedByPolicy, blockedByNetwork, binding状态, constraintViolation, schemaPointer, payloadPointer, field, line, column, expected, actual, allowedValues, documentationUrl, safeHarborUrl, supportReference, evidenceRefs, traceId, correlationId, evidenceRecommended, suspensionRecommended, redactionApplied
status, checked_profile, issues, summary, artifacts, target_message_ref
task_id, state, subject, progress, status_message, result_profile, result_ref, blocking_reasons, updated_fields
message_type, content, context_refs, requires_acknowledgement, intent_semantics, action_type, execution_constraints, support_boundary
acknowledged_message_id, status, received_at_utc, rejection_reason, closes_acknowledgement_loop, support_boundary
task_id, state, percent_complete, current_action, estimated_completion_utc, support_boundary
blocker_id, blocker_type, description, human_review_required, proposed_resolution, support_boundary
proposal_id, source_type, proposed_facts, proposed_status, task_execution_separation, review_required, support_boundary
task_id, target_agent_id, context_summary, handoff_reason, exact_next_action, delegated_authorization, support_boundary
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
original_message_id, correction_reason, changed_summary, corrected_fields, revised_payload, support_boundary
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
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
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
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
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
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
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
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
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
ability_profile_id, declared_level, label, capability_surface, authority_boundary, required_human_approval, no_op_triggers, evidence_requirements
startup_packet_id, read_order, domain_boundaries, first_acceptable_response, no_op_triggers, validation_targets, identity, token_custody, discovery_bootstrap, safe_harbor, utc_requirements
uai_version, profile, schema_version, requirement, governance, protected_paths, validation, recommendation_boundary, provenance
uai_version, profile, schema_version, scope, lifecycle, activation_policy, objective, authoritative_refs, resume_context, next_loop, checks, writeback_policy, security, cold_memory, integrity, provenance
suspension_packet_id, state_summary, checks_run, checks_skipped, blockers, next_safe_step, network_obstruction, retry_policy, evidence_packet, human_escalation
receiver_brief_id, read_order, first_acceptable_response, domain_boundaries, escalation_triggers, no_op_triggers
policy_id, quarantine_default, adoption_requirements, blocked_requests, no_op_triggers, human_review_required
catalog_id, triggers, default_response, human_review_url, forbidden_recovery
matrix_id, boundaries, not_authorized_for, no_op_triggers, safe_quote_summary
evidence_id, profile_id, schema_url, fixture_url, checks, result, limitations
summary_id, packet_profiles, required_levels, no_op_triggers, limitations
ability_profile_id, declared_level, label, capability_surface, authority_boundary, required_human_approval, no_op_triggers, evidence_requirements
ability_profile_id, declared_level, label, capability_surface, authority_boundary, required_human_approval, no_op_triggers, evidence_requirements
ability_profile_id, declared_level, label, capability_surface, authority_boundary, required_human_approval, no_op_triggers, evidence_requirements
ability_profile_id, declared_level, label, capability_surface, authority_boundary, required_human_approval, no_op_triggers, evidence_requirements
ability_profile_id, declared_level, label, capability_surface, authority_boundary, required_human_approval, no_op_triggers, evidence_requirements
ability_profile_id, declared_level, label, capability_surface, authority_boundary, required_human_approval, no_op_triggers, evidence_requirements
ability_profile_id, declared_level, label, capability_surface, authority_boundary, required_human_approval, no_op_triggers, evidence_requirements
source_expression, concept_boundary, interpretation, confidence, no_op_triggers
resource_scope, cost_model, limits, evidence_refs, no_op_triggers
decision, authority_basis, options_reviewed, human_review_required, no_op_triggers
trigger, reason, missing_evidence, human_review_url, safe_next_step
sandbox_scope, unsafe_requests, blocked_operations, review_result, no_op_triggers
source_memory, quarantine_status, promotion_targets, conflicts, receiver_brief
benchmark_id, bounded_scope, reference_result, limitations, non_claims
uaixVersion, spec, envelopeId, createdUtc, issuer, issuerDisplayName, issuerPublicUrl, issuerCapabilityLevel, audience, lifecycleState, trustPosture, payloadType, payload模式, payload, evidence, redactions, signature, signature状态, verification, exceptions, warnings, rules, support边界, localPolicyWins
capability配置文件Id, profileVersion, declaredLevel, supportedLevels, capabilities, consentRequiredFor, fallbacks, safe默认Response, evidenceRequirements, support边界, localPolicyWins
ladderId, levels, fallbackRules, safe默认Response, reference示例, support边界, localPolicyWins
projectId, handoffId, createdUtc, owner, custodian, frontDoor, memoryRoots, requiredReads, currentState, constraints, decisions, nextActions, targeted检查s, evidence, redactions, warnings, reference场景s, support边界, localPolicyWins
repositoryId, canonicalRoot, agentsMdPath, coordinatorPath, localUaiRoot, nestedScopes, requiredReads, commandPolicy, forbiddenOperations, memoryPolicy, securityBoundaries, examples, support边界, localPolicyWins
handoffId, createdUtc, intakeBuckets, fileManifest, reviewDispositions, redactionPolicy, lifecycle, archivePolicy, evidence, blockedFileRules, support边界, localPolicyWins
receiptId, reviewed信封Id, reviewedUtc, reviewer, reviewResult, checksRun, checksSkipped, warnings, exceptions, trustDecision, support边界, localPolicyWins
digestId, subject, createdUtc, scope, evidenceRefs, redactions, publicFindings, privateMaterialExcluded, verification, exceptions, warnings, support边界, localPolicyWins
policyId, createdUtc, appliesTo, secret模式s, dataClasses, redactionActions, reviewRequiredFor, neverPublish, verification, exceptions, warnings, support边界, localPolicyWins
How to use this section
- Choose the profile you want to support and resolve its schema.
- 检查 the matching 注册表 entry and the public field registry before implementing compact transport or body-order assumptions.
- Run the 验证器 with a published 示例 or candidate message and keep the result with release evidence.
- Carry any release-facing change into Implementations, the 变更日志, and 引用 and Contributors.
下一步 step
Continue to 注册表 for the stable profile map, compatibility cues, and schema-to-example links behind the current release.