Connection check
verified live · 27h ago
values-firewall
EU AI Act Art-14 runtime oversight: allow / flag / gate-to-human on an agent action, with receipt.
Tools
3
GitHub stars
—
Installs / wk
—
Licence
—
Transport
streamable-http
Last checked
27h ago
Tools & capabilities
3 toolsRead from the running server on 27h ago.
check_action
action*context
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 princip… 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
action*context
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, valu… 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