M5：百工与司命——能力注册表、授契行契请命、禁域裁决与观察标证

- 百工域 domains/baigong：capabilities（统一能力契约：执行类型 builtin/qiankun/mcp/http + 四维风险标注 + 来源版本）、mandates（授契 grant / 行契 charter 预算时间窗，撤销立即生效）、tool_calls（净化摘要 + 观察标证）；请命复用 pending_confirmations 加 expires_at/brief_json（超时=拒绝执行 HJ-1302，六要素说明）
- 司命裁决器 siming.py：四维取最高档（能力/数据/后果/情境）；禁域为代码常量不可配置（递归删根/格式化/写裸设备/fork 炸弹、file:// 协议、密钥材料外发）——专项测试断言恶意标注与篡改对象仍拒 HJ-1301
- 执行链：禁域→裁决（HJ-1303 未授契拒且双留痕）→请命→执行（乾坤经 SandboxClient HMAC；MCP 经 call_tool；内置无副作用）→净化标证（观察非事实，敏感遮蔽+体量截断）→行动账
- MCP 登记/启停/刷新自动派生与撤下 capabilities（博闻登记接入点）；内置能力种子（echo/datetime/qiankun.shell/web.fetch）
- 端点：/capabilities /mandates /petitions /tool-calls + /tools 兼容投影；前端百工页四区（能力目录四维标注/授契行契/请命批准拒绝/行动账观察标证）
- 退役：modules/safety|skills|tool_runtime|agent、application/tool_runtime、services/skills|safety、tool_policies/skills/model_endpoint_overrides 表（迁移 006）、前端 SkillManager/ToolsConsole/旧 tools 页
- 验收（test_baigong_siming 四用例）：未授契被拒留痕、请命超时不执行、禁域不可关闭、结果为观察不入忆；后端 454、前端 220、BFF 4、神识 5 包全绿（2 个预存环境失败不变）

backend/app/services/serializers.py

@@ -12,7 +12,6 @@ from app.models.governance import (
     Goal,
     PerceptionChannel,
     Plan,
-    ToolPolicy,
     WorldEntity,
 )
 from app.models.imports import CharacterImportJob, ImportItem
@@ -35,7 +34,6 @@ from app.schemas.imports import ImportItemResponse, ImportJobResponse
 from app.schemas.personality import PersonalityProposalResponse, PersonalityResponse
 from app.schemas.preferences import GenerationPreferencesResponse
 from app.schemas.runtime import EventResponse, RunResponse
-from app.schemas.safety import SafetyPolicyItem, ToolPolicyResponse
 from app.schemas.world import (
     WorldEntityResponse as CharacterWorldEntityResponse,
 )
@@ -301,34 +299,6 @@ def audit_to_response(event: AuditEvent) -> AuditEntry:
     )
 
 
-def tool_policy_to_response(policy: ToolPolicy, *, executable: bool = False) -> ToolPolicyResponse:
-    """工具策略完整元数据；executable 由调用方按 builtin/registered specs 派生。"""
-    return ToolPolicyResponse(
-        name=policy.name,
-        description=policy.description,
-        risk_level=policy.risk_level,
-        permission_policy=policy.permission_policy,
-        side_effect=policy.side_effect,
-        audit_required=policy.audit_required,
-        source=policy.source,
-        enabled=policy.enabled,
-        executable=executable,
-        created_at=to_iso(policy.created_at),
-        updated_at=to_iso(policy.updated_at),
-    )
-
-
-def tool_policy_to_safety_item(policy: ToolPolicy) -> SafetyPolicyItem:
-    """策略子集（§16 GET /safety/policies 元素）。"""
-    return SafetyPolicyItem(
-        tool=policy.name,
-        risk_level=policy.risk_level,
-        permission_policy=policy.permission_policy,
-        side_effect=policy.side_effect,
-        audit_required=policy.audit_required,
-    )
-
-
 def import_job_to_response(job: CharacterImportJob) -> ImportJobResponse:
     return ImportJobResponse(
         id=job.id,