mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-11-06 05:17:15 +00:00
chore(catalog): review disclosure for hermes-axioma
This commit is contained in:
1 parent
96196a34b9
commit
872564c166
1 file changed
+1
-1
@@ -3,7 +3,7 @@ repo: https://github.com/percyhendrux123-prog/hermes-axioma
|
||||
sha: "fdd1fee06a2e63ffa3eb74f8e894c626c9b0651e"
|
||||
version: "0.3.0"
|
||||
title: Axioma
|
||||
description: "Inline signal color in the agent's normal reply. The agent marks the few phrases that deserve a second look (stop, caution, go, whisper) and the plugin renders them per surface with color, a style cue and a word, never color alone: Desktop through KaTeX color, CLI/TUI through truecolor ANSI, Telegram/Discord/Slack as bold plus the word, SMS and email as the word only. Green renders only when a tool call Hermes reported as successful in this session backs it; a rarity budget caps marks per reply; malformed tags never leak. A color-vision-safe palette and a style-and-words-only mode are one setting away. Secondary: an advisory card (intent, light, signal, question) staged before configured send/spend/spin/scrub tool calls and shown through Hermes's own approval prompt. Each card and notice carries a short card code (a keyed hash of the exact text shown, the tool, its arguments and the card id), logged when shown and again with the answer; /signals verify <code> reports in plain words whether what was staged, shown and answered line up (spec section 5.6, shown equals staged). Advisor, not a gate: it never blocks, approves or executes anything. Disclosure: no network, model calls, subprocesses, background threads, telemetry or credential reads (agent.secret_scope.get_secret is used for presence only, for an optional provider-conflict check); writes flag metadata, salted span hashes and keyed card-code digests (no message bodies) to an owner-only (0600) SQLite file, with the card-code key in a separate owner-only file, under its own plugin data directory; adds a short markup guide to the system context through pre_llm_call."
|
||||
description: "Inline signal color in the agent's normal reply. The agent marks the few phrases that deserve a second look (stop, caution, go, whisper) and the plugin renders them per surface with color, a style cue and a word, never color alone: Desktop through KaTeX color, CLI/TUI through truecolor ANSI, Telegram/Discord/Slack as bold plus the word, SMS and email as the word only. Green renders only when a tool call Hermes reported as successful in this session backs it; a rarity budget caps marks per reply; malformed tags never leak. A color-vision-safe palette and a style-and-words-only mode are one setting away. Secondary: an advisory card (intent, light, signal, question) staged before configured send/spend/spin/scrub tool calls and shown through Hermes's own approval prompt. Each card and notice carries a short card code (a keyed hash of the exact text shown, the tool, its arguments and the card id), logged when shown and again with the answer; /signals verify <code> reports in plain words whether what was staged, shown and answered line up (spec section 5.6, shown equals staged). Advisor, not a gate: it never blocks, approves or executes anything. Disclosure — before configured send/spend/spin/scrub tool calls (by default send_message, email/post/publish tools, payment/checkout tools, cron and kanban creation, delegate_task, terminal deploy and git push/gh pr commands, and terminal rm/mv when no workspace is configured) it escalates the call to Hermes's own approval prompt with an advisory card, using a fresh rule key each time so remembered Session/Always approvals never skip later prompts; under cron and other unattended runs Hermes's approval policy (default deny) then refuses those calls; it never auto-approves or executes anything, makes no network, model or subprocess calls, reads credentials only as presence checks through agent.secret_scope, adds a short markup guide to the system context through pre_llm_call, rewrites the agent's reply text to render the marks, and writes metadata, salted span hashes and keyed card-code digests (no message bodies) to an owner-only SQLite file plus a separate owner-only key file under its own plugin data directory."
|
||||
maintainer: percyhendrux123-prog
|
||||
tier: community
|
||||
category: tools
|
||||
|
||||
Reference in new issue
Block a user