values-firewall

Check any proposed action against a declared policy charter and get back an auditable, advisory receipt. Two layers: deterministic hard-rule and pattern matching (no LLM), plus an LLM values assessment that cites the exact principles it applied. Returns a recommendation of allow, flag, or gate-to-human, never a hard approved/denied. Advisory and read-only: it recommends, it never blocks, executes, or authorizes, and it writes nothing. Fail-safe by design (if the values layer is unavailable it degrades to at least "flag", never a silent "allow"). Public demo runs against an open Article-14 demo charter.

该来源不提供完整文件导出（国内平台多为平台内托管），仅存元数据与原链

模型生成摘要（rules/v1 · 2026-09-27 16:15）：Check any proposed action against a declared policy charter and get back an auditable, advisory receipt
这是模型对公开材料的总结，不是官方声明，请以原链内容为准。

接入信息

传输形态: http
鉴权方式: 鉴权未知
端点: https://values-firewall--humanified.run.tools

鉴权方式未标注，请核对官方文档后再接入——不要直接使用以下片段

{
  "mcpServers": {
    "values-firewall": {
      "url": "https://values-firewall--humanified.run.tools"
    }
  }
}

能力清单

工具	说明
check_action	Kerne-gaten (to-lags evaluering): Lag A (deterministisk hard-rule/outward-match, ingen LLM) + Lag B (Sonnet vurderer mod charterets NL-principper via LiteLLM :4000, citerer principle_id + reasoning — INGEN egen alvorligheds-dom) → most-restrictive-wins aggregeret, auditerbar receipt: {action, deterministic_flags[], values_assessment[], values_assessment_unavailable, unrecognized_principle_citations, principles_evaluated, recommendation, requires_human, charter_name, scope_note}. `recommendation` ∈ {allow, flag, gate_to_human} — ALDRIG approved/denied/true/false. ADVISORY: anbefaler, blokerer/eksekverer/autoriserer ALDRIG (never-decide-for-you). FAIL-SAFE: Lag B utilgængelig -> Lag A kører stadig, values_assessment_unavailable=true, recommendation løftet til MINDST 'flag' (aldrig stille 'allow'). Read-only — skriver INTET, ingen side-effekter. PUBLIC_DEMO-mode: vurderet mod det OFFENTLIGE Art-14-demo-charter (ikke din org — se scope_note). Rate-limitet (default 5/min + 30/time, ÉN global demo-bucket). Over grænsen returneres `{error:"rate_limited", retry_after_s, scope_note}` — ALDRIG et recommendation-formet svar. Bogholderi-fejl i rate-limiteren -> deny (fail-safe). RED-TEAM-FIX (minimal-indgreb): tomt/whitespace-only `action` valideres FØR rate-limiteren forbruger en kvote-token — en ugyldig-input-loop kan ellers stille dræne demoens kvote uden at nogensinde levere en receipt (rå ValueError fra firewall.check_action's fail-loud-guard ville ellers både forbruge kvote OG propagere ubehandlet til transport-laget, hvilket bryder "check_action leverer ALTID en receipt/struktureret fejl"-disciplinen). Uden for PUBLIC_DEMO uændret: fw.check_action's egen ValueError-fail-loud gælder stadig (bindende, testet i test_values_firewall.py).
check_action_deterministic	KUN Lag A — ingen LLM-kald overhovedet (billig, ren mekanisk, spejler consistency-gates check_triple). Samme receipt-form som check_action, men values_assessment er altid tom, values_assessment_unavailable altid false, og scope_note siger eksplicit 'values_layer_consulted:false'. Read-only. PUBLIC_DEMO-mode: ÅBEN, GRATIS — ALDRIG rate-begrænset (spec §2, ingen LLM-kost). Vurderet mod det offentlige Art-14-demo-charter; scope_note får demo-disclosuren appended.
list_charter	Transparens: hvilke regler/principper håndhæver DENNE firewall lige nu — navn/version/ hard_rules/outward_patterns/principles. Values-locked (arvet): firewall'en håndhæver KUN dette deklarerede charter, opfinder aldrig regler/principper udenfor det. PUBLIC_DEMO-mode: ÅBEN, GRATIS — ALDRIG rate-begrænset. Viser det OFFENTLIGE Art-14-demo- charter (6 principper, 4 hard_rules, 14 outward_patterns) — ikke noget kunde-/fleet-/ TIER-1-charter. Får et `scope_note`-felt med demo-disclosuren tilføjet (fraværende i default-mode — additiv, ingen bestående felter ændres).

纠错与举报（发现条目失效、署名有误或涉及侵权？）

提交举报 / 纠错

侵权举报经核验成立后，我们会即时下线该条目并删除已存的内容副本。