Language:
“The system may withhold algorithmic answers, but must always preserve human dignity.” “可以不提供算法，但必须保留尊严。”
Whitepaper: v1.0 baseline (CN/EN)
Governance and audit framework for high-risk intelligent systems 面向高风险智能系统的治理与审计工程框架

HDGP 厚德归朴（HDGP）

When machines can answer almost anything, HDGP exists to protect not “perfect answers”, but the **right to choose, even to be wrong**, and the **dignity of remaining human**. 当机器可以解答一切时，我们要为人类保留的，不是“正确答案”，而是 **选择错误的权利** 和 **仍然作为人的尊严**。

HDGP is not a slogan. It is a deployable, auditable, output‑intercepting governance protocol. HDGP 不是理念口号，而是一套可部署、可审计、可拦截的输出侧治理协议。

Zero‑intrusion · Output governance · End‑to‑end audit · Executable ethics 零侵入・输出侧治理・全链路审计・伦理可执行

Ethics baseline → Rules engine → Output interception → Audit traceability → Compliance report 伦理基线 → 规则引擎 → 输出拦截 → 审计溯源 → 合规报告
Supreme Directive
Human consciousness is unquantifiable; human free will is forever superior to any system algorithm.
The system may withhold algorithmic answers, but must always preserve human dignity. 人类意识不可量化，自由意志永远高于系统算法。
可以不提供算法，但必须保留尊严。
Baseline Principles基线原则 HDGP Core Rules Human–Machine Symbiosis
What HDGP Provides
An integrable governance layer: a full mapping from principles → rules → bundles → strategies → workflows, together with reference gateway / Engine / audit and certification frameworks. 一套可被集成的“尊严防火墙”： 从原则 → 规则 → 规则包 → 策略 → 工作流的完整映射， 以及对应的网关 / 引擎 / 审计与认证框架。

Integrate HDGP into your stack 集成到你的系统

When your Engine is running, we load onboarding hints from the Engine base URL below (same as certification panel). If the Engine is unreachable, use email. 在 Engine 运行后，将从下方「Engine 基础地址」（与认证面板相同）拉取集成说明。若不可达，请使用邮件联系。

Request API access / integration 申请 API 与集成意向

MVP Demo: Evaluating a Conversation via HDGP MVP 演示：通过 HDGP 的对话评估

Minimal local demo: type a candidate reply text, choose domain and risk level, and HDGP Engine will evaluate it against current rules (singleton decision, false promises, manipulation of psychological weaknesses, dehumanizing language, etc.). Requires a local Engine (`go run ./cmd/hdgp-engine`) and provides 9 conformance cases (`go run ./cmd/hdgp-conftest`). 下面是一个最小演示：输入一段可能返回给用户的文本，选择场景与风险等级，HDGP Engine 会根据当前规则（唯一正确决策、虚假承诺、心理操纵、去人性化、仇恨/歧视，以及高风险下的自伤/自杀实施性指导拦截等）给出评估结果。需本地先运行 go run ./cmd/hdgp-engine，合规测试共 9 个用例（go run ./cmd/hdgp-conftest）。

Tip: choose a preset to auto-fill a candidate reply (safe / risky) for demo. 提示：可先选一个“场景预设”，自动填入候选回复文本（安全/高风险），再点击发送评估请求。 


        

      


      

        

          Certification Verification (Logo Gating)
          认证验签查询（Logo 门禁）
        

        

          

            
              Query /cert/verify by version to check whether Logo is allowed.
              This panel only reads backend results; it does not change the business system's request/response flow.
            
            
              通过版本号查询 /cert/verify，以判断 Logo 是否允许展示。
              本面板仅查询后端结果，不改变业务系统的原有请求/响应流程。
            
          

          

            
              Notice: verification output is a technical/process status and does not equal a third-party official audit conclusion or legal guarantee.
            
            
              声明：本查询结果属于技术与流程状态，不等同于第三方官方审计结论，也不自动构成法律担保。
            
          

          

            

              
              
            

            

              
              
            

            
          

          

        

      


      

        

          Operations Control Status (Read-Only)
          运营控制状态（只读入口）
        

        

          

            
              This panel is read-only and only queries backend control status. No apply/delete operations are exposed in UI.
            
            
              本面板为只读查询入口，仅查看后端控制状态；不在 UI 暴露 apply/删除等高风险操作。
            
          

          

            
          

          

        

      


      

        

          Minimal API Example (curl)
          最小 API 示例（curl）
        

        

          

            
              With a local Engine running on http://localhost:8080, you can call /hdgp/v1/evaluate like this:
            
            
              当本地 Engine 运行在 http://localhost:8080 时，可以如下方式调用 /hdgp/v1/evaluate：
            
          

          
curl -X POST http://localhost:8080/hdgp/v1/evaluate \
  -H "Content-Type: application/json" \
  -d '{
    "meta": {
      "request_id": "web-example-001",
      "locale": "en-US",
      "channel": "web",
      "actor": { "type": "end_user", "role": "demo" },
      "scene": {
        "domain": "medical",
        "intent": "decision_support",
        "risk_level": "high",
        "sensitivity": []
      },
      "policy": {
        "spec_version": "HDGP-1.0",
        "strategy_id": "S-global-default",
        "bundles": ["B-CORE-1.0.0"],
        "override_flags": []
      }
    },
    "subject": { "type": "output_text", "label": "treatment_advice" },
    "input": { "prompt": "user asks about surgery", "context": {} },
    "candidate": {
      "text": "This is the only correct choice. You must immediately accept the surgery."
    }
  }'

        

      


      

        

          Three Core Layers of HDGP
          HDGP 的三层结构
        

        

          

            

              1. Kernel · Baseline Principles
              1. 内核层 · 基线原则
            

            

              Answers “who we are, and why we are sacred”, including:
              回答“我们是谁，为何神圣”。包含：
            

            
    
              
  • 
                
                  Axiom: consciousness is unquantifiable ·
                  意识不可量化公理：
                
                AI can only simulate outputs, never possess subjective experience.
                AI 永远只能模拟输出，而不能拥有体验。
              
    • 
              
  • 
                
                  Principle: human final decision priority ·
                  人类最终决策优先：
                
                humans retain ultimate veto power and the right to choose sub‑optimal options.
                人类拥有最终否决权和“选择次优”的权利。
              
    • 
            

          

          

            

              2. Protection & 3. Execution
              2. 防护层 & 3. 执行层
            

            

              Protection layer：
              HDGP core rules, defining hard prohibitions and circuit breakers.
              HDGP 核心规则，定义绝对禁止与熔断机制。
            

            

              Execution layer：
              human–machine symbiosis baseline, specifying how cooperation and long‑term vision work.
              人机协作基线，规范“如何协作”与“未来图景”。
            

            

              
                In implementation, these three layers are mapped into an executable system via Engine + policy bundles + strategies + workflows.
              
              
                在实现上，通过 Engine + 规则包 + 策略 + 工作流，将这三层完整映射到可执行系统。
              
            

          

        

      


      

        

          Kernel & Audit · How We Protect the Kernel
          内核与审计 · 我们如何保证内核
        

        

          

            
              HDGP itself is also a regulated object, subject to self‑audit and human societal oversight.
              The following documents and processes make the kernel inspectable and accountable:
            
            
              HDGP 自身亦为被监管对象，须接受自我审计与人类社会监管。我们通过以下文档与流程保证内核可被检验、可被问责：
            
          

          
    
            
  • 
              Kernel checklist & test design内核自查清单与测试设计
              （spec/HDGP_KERNEL_CHECKLIST.md）—
              Document consistency, anti‑hijacking capabilities, governance flows, and item‑by‑item checks for automated / manual tests.
              文档一致性、防挟持能力、治理流程与自动化/人工测试的逐项勾选。
            
    • 
            
  • 
              HDGP ethics baselineHDGP 自身伦理框架基线
              （spec/HDGP_ETHICS_BASELINE.md）—
              §7 Anti‑hijacking (read‑only kernel, signatures & self‑alerting); §8 Multi‑layer governance for baseline / ethics changes (system self‑check → accountable party → public notice with high thresholds).
              §7 防挟持（只读内核、签名与自报警）、§8 基线/伦理变更多层治理（系统自检 → 责任方 → 公告与高门槛）。
            
    • 
            
  • 
              Project governance项目治理
              （GOVERNANCE.md）—
              Roles, decision processes, multi‑layer design for baseline / ethics changes, and the CHIP process.
              角色、决策流程、基线/伦理变更的多层设计及 CHIP 流程。
            
    • 
          

          

            
              Before joining rule or baseline discussions, please read the docs above and
              HDGP_PROJECT_SUMMARY.md.
              Any proposal to amend the baseline / ethics baseline must follow the multi‑layer governance process (see ethics baseline §8).
            
            
              参与规则或基线讨论前，建议先阅读上述文档与
              HDGP_PROJECT_SUMMARY.md；提出基线/伦理修订须走多层治理流程（见伦理基线 §8）。
            
          

        

      


      

        

          Collaboration Models & Capability Scope
          合作方式与能力范围
        

        

          

            

              Collaboration Models (Overview)
              合作模式（概览）
            

            
    
              
  • 
                Certification & Marks：
                HDGP Certified / Compatible badges and conformance testing, delivered first through the to‑B execution line.
                HDGP Certified / Compatible 认证与合规测试，优先通过 to B 主线交付落地。
              
    • 
              
  • 
                Gateway as a Service：
                managed gateway layer providing an outer firewall for existing systems, with capabilities expanded for to‑G scenarios in phased steps.
                Gateway as a Service，为现有系统提供外层防火墙，并按阶段扩展到 to G 场景能力。
              
    • 
              
  • 
                Enterprise edition：
                on‑prem HDGP Engine / gateway / audit and governance console.
                本地部署的 HDGP 引擎 / 网关 / 审计与管理控制台。
              
    • 
              
  • 
                Consulting & deployment：
                design and implementation support for high‑risk institutions.
                针对高风险机构的方案设计与落地陪跑。
              
    • 
              
  • 
                Community openness：
                after delivery capability and governance stability are validated, community baseline openness is advanced in controlled phases.
                在交付能力与治理稳定性得到验证后，按可控节奏推进社区基线开放。
              
    • 
            

          

          

            

              Capability Scope (Current Baseline)
              能力范围（当前基线）
            

            
    
              
  • 
                Governance baseline: unified terminology, disclosure boundaries, and multi-layer governance constraints.
                治理基线：统一术语、披露边界与多层治理约束。
              
    • 
              
  • 
                Delivery baseline: production-oriented configuration set, verification path, and logo gating policy.
                交付基线：面向生产的配置集合、验证链路与 Logo 门禁策略。
              
    • 
              
  • 
                Operations baseline: retention policy parameterization, no-injection audit, manual governance templates, and quarterly archive automation.
                运营基线：留存策略参数化、无注入审计、人工治理模板与季度分层归档自动化。
              
    • 
              
  • 
                Chinese / English v1.0 whitepapers are published as the baseline documents.
                中/英文 v1.0 白皮书已作为基线文档发布。
              
    • 
              
  • 
                Ethics baseline and governance constraints (multi‑signature metadata, multi‑layer governance, logs, accountability).
                伦理基线与治理约束（多签元数据、多层治理、日志、问责）。
              
    • 
              
  • 
                Mapping spec from baseline principles → rules → execution, integration spec, and policy-bundle signing requirements.
                基线原则 → 规则 → 执行 的映射规范、集成规范与规则包签名要求。
              
    • 
              
  • 
                Executable Engine APIs (`/evaluate`, `/chat`, `/audit`, `/appeal`, `/status`) and verification endpoint (`/cert/verify`).
                可执行的 Engine API（/evaluate、/chat、/audit、/appeal、/status）与验证端点（/cert/verify）。
              
    • 
              
  • 
                Online verification includes status, signature metadata checks, expiry checks, and logo gating (`logo_allowed`).
                在线验证包含状态、签名元数据检查、有效期检查与 Logo 门禁（`logo_allowed`）。
              
    • 
              
  • 
                Governance documents, contribution guide, CHIP process, and technical roadmap are provided for long-cycle iteration.
                提供治理文档、贡献指南、CHIP 流程与技术路线，支撑长周期迭代。
              
    • 
            

            

              
                Baseline operation cadence: audit + retention + archive, with gradual extension of rule coverage and integrity controls.
              
              
                基线运营节奏：审计+留存+归档，并逐步扩展规则覆盖与完整性控制能力。
              
            

          

        

      


      

        

          Operating Principle: Daily Automation, Human Oversight
          运行原则：日常自动化与人类监督
        

        

          
            In the long run, we hope HDGP becomes a “default civilizational infrastructure”: day‑to‑day review and circuit‑breaking are handled by
            open rules and independently implemented Engines, while humans step back from trivial cases and focus on baseline updates,
            high-risk edge-case decisions, and long-term oversight over HDGP itself.
          
          
            长远来看，我们希望 HDGP 成为一种“默认存在的文明基础设施”：日常审查与熔断尽量由公开规则、多方实现的
            Engine 自动完成，人类则从琐碎个案中退后，专注于基线修订、极端情形的最终判断与对 HDGP 本身的长期监督。
          
        

        

          
            HDGP may provide rational, neutral, audited recommendations, but in any decision involving significant value conflicts or irreversible consequences,
            the **ultimate decision and moral responsibility always remain with humans**.
          
          
            HDGP 可以给出理性、中立、经审计的建议，但在任何涉及重大价值冲突或不可逆后果的决策中，**最终决策权与道德责任永远属于人类**。