hermes-admin/hermes-agent
1
0
Fork 0
Code Issues Pull Requests Actions 5 Packages Projects Releases Wiki Activity

chore(catalog): merge-side review chores for salesforce-chatter, liquid-inference-provider, deepgram-voice (sweep 1010)

Browse Source 
- salesforce-chatter, liquid-inference-provider: replace the Disclosure with the reviewed `Disclosure —` line.
- deepgram-voice: requires_env is DEEPGRAM_API_KEY (was a literal `name`), matching plugin.yaml.
This commit is contained in:
teknium1
2026-10-09 21:20:24 -07:00
committed by Teknium
parent 4117f8fe51
commit 5a487bcaeb
3 changed files with 3 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
plugin-catalog/deepgram-voice.yaml
View File

@@ -11,4 +11,4 @@ capabilities:
provides_hooks: []
provides_middleware: []
requires_env:
- name
- DEEPGRAM_API_KEY

12
plugin-catalog/liquid-inference-provider.yaml
View File

@@ -1,17 +1,7 @@
name: liquid-inference-provider
repo: https://github.com/architect-xyz/hermes-liquid-inference
sha: acd120f007367c1f422d3cd6ffe643f916f0b5f7
description: >-
Liquid Inference, an auction exchange for LLM inference, as a Hermes model provider (provider id
`liquid`): the exchange sends each request to the eligible offer with the lowest estimated charge,
and each request carries a cap on its charge (1 USD by default; set
`model.default_headers.x-liquid-cap-usd` to change it). Submitted by Architect, the operator of
Liquid Inference. Disclosure — registers one model provider at import and nothing else (no tools,
hooks, commands or threads); chat requests and the model list go to
https://router.inference.ai.exchange/v1 (or LIQUID_BASE_URL) through Hermes' own client with
LIQUID_API_KEY, which Hermes reads; each chat request carries the headers `X-Title: Hermes Agent`
and `x-liquid-cap-usd`, and a top-level `reasoning_effort` only when the user selects a level; the
plugin itself opens no connections, reads and writes no files and starts no processes.
description: "Liquid Inference, an auction exchange for LLM inference, as a Hermes model provider (provider id `liquid`): the exchange sends each request to the eligible offer with the lowest estimated charge, and each request carries a cap on its charge (1 USD by default; set `model.default_headers.x-liquid-cap-usd` to change it). Submitted by Architect, the operator of Liquid Inference. Disclosure — registers one model provider at import and nothing else (no tools, hooks, commands or threads). Chat requests (full prompts and tool results), auxiliary tasks (model `liquid.auto`) and the model list go through Hermes's own client to https://router.inference.ai.exchange/v1 (or LIQUID_BASE_URL) with LIQUID_API_KEY. The exchange forwards each request to whichever third-party provider wins its auction. Each request is billed up to its `x-liquid-cap-usd` cap (1 USD by default, set with `model.default_headers.x-liquid-cap-usd`) and carries `X-Title: Hermes Agent`. A top-level `reasoning_effort` is sent only when you select a level."
maintainer: architect-xyz
tier: community
category: models

2
plugin-catalog/salesforce-chatter.yaml
View File

@@ -3,7 +3,7 @@ repo: https://github.com/zenplace-system/hermes-plugin-salesforce-chatter
sha: 16ff469ffb1484e37053315e799846d3c4d7c9d8
subdir: salesforce_chatter
title: Salesforce Chatter
description: "Talk to Hermes from Salesforce Chatter: @mention the bot user in a post or comment, it Likes the message as an acknowledgement and replies in the same thread, keeping the thread as one session. Images and files on the post are passed to the model; MEDIA files are attached back. Community plugin, not affiliated with Salesforce. Disclosure: authenticates as a dedicated bot user with the OAuth 2.0 JWT bearer flow, reading the private key file at SF_CHATTER_PRIVATE_KEY_PATH; talks to the configured Salesforce login host and the org instance (attachment downloads follow Salesforce redirects); polls the To Me feed every 60 s and, for allowlisted groups, runs a SOQL CollaborationGroupFeed probe every 5 s by default, which counts against the org's API quota; writes Likes, comments, file uploads to the bot user's Files and optional home-channel posts; stores its handled-message ledger in <HERMES_HOME>/plugin-data/salesforce-chatter/inbox.sqlite. dry_run defaults to true (no Salesforce writes); while SF_CHATTER_ALLOWED_USERS is unset nobody is answered and /approve /deny never reach the agent. Optional, off by default: html_preview renders model-generated HTML to PNG with Chromium inside a network-isolated Docker container. No telemetry."
description: "Talk to Hermes from Salesforce Chatter: @mention the bot user in a post or comment, it Likes the message as an acknowledgement and replies in the same thread, keeping the thread as one session. Images and files on the post are passed to the model; MEDIA files are attached back. Community plugin, not affiliated with Salesforce. Disclosure — authenticates as a dedicated bot user with the OAuth 2.0 JWT bearer flow, reading the private key file at SF_CHATTER_PRIVATE_KEY_PATH; talks to the configured Salesforce login host and the org instance (attachment downloads follow Salesforce redirects); image URLs in the agent's replies are fetched from the gateway host over HTTPS (any public host; private, loopback and metadata addresses are refused) and uploaded to Chatter; polls the To Me feed every 60 s and, for allowlisted groups, runs a SOQL probe every 5 s by default (counts against the org API quota); writes Likes, comments, files in the bot user's Files and optional home-channel posts; keeps its ledger in plugin-data/salesforce-chatter/inbox.sqlite. dry_run defaults to true (no Salesforce writes, no outbound image fetch); with SF_CHATTER_ALLOWED_USERS unset nobody is answered. Optional, off by default: html_preview renders model-generated HTML to PNG with Chromium in a network-isolated Docker container (digest-pinned image, pulled if missing). No telemetry."
maintainer: zenplace-system
tier: community
category: platform