mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-11-06 05:17:15 +00:00
chore(catalog): review disclosure for ppq-provider
This commit is contained in:
1 parent
a1829b3527
commit
ba116c9bb5
2 files changed
+18
-18
No files matched your search
@@ -1,18 +0,0 @@
|
||||
# ppq-provider — catalog manifest. Pinned to the ppq-hermes-provider commit below.
|
||||
name: ppq-provider
|
||||
repo: https://github.com/thepurpose-npub/ppq-hermes-provider
|
||||
sha: 94a6686fe4759d6fbd627a3ad58c9e1fcdb0b081
|
||||
subdir: model-providers/ppq
|
||||
description: "PayPerQ (ppq.ai) OpenAI-compatible model provider for Hermes — per-response cost estimation from ppq's published rate card, chat model discovery from GET /v1/models, automatic per-request Zero Data Retention opt-in, and a 3-layer picker pin strategy (user-local pins file → live top chat models from ppq's public stats dashboard → generic static fallback; generic installs never get the author's personal pins). Disclosure — model provider; PPQ_API_KEY and all prompts, tool schemas and responses go to ppq.ai (PayPerQ), a relay that routes requests to third-party inference partners, some outside the user's jurisdiction, and frontier providers still see prompts. Privacy protections are opt-in per request: for models badged privacyLevel 'zdr' the plugin automatically sends provider={\"zdr\": true, \"data_collection\": \"deny\"} so requests route only to endpoints with a Zero Data Retention policy that do not collect data (the zdr model set refreshes hourly from GET /v1/models with a pinned fallback); models badged 'e2e' run inside TEE enclaves with no opt-in flag needed — enclave coverage applies to chat by default, not to image/video/audio, and true end-to-end encryption is only available via the optional local ppq-privacy-verifier proxy. Additional caveats: Claude Opus 4.8 with web search enabled drops the ZDR guarantee, and some Anthropic/Gemini models may override the provider routing fields (order/only/ignore)."
|
||||
maintainer: thepurpose-npub
|
||||
tier: community
|
||||
category: models
|
||||
requires_hermes: ">=0.21.3"
|
||||
docs_url: https://github.com/thepurpose-npub/ppq-hermes-provider#readme
|
||||
version: "0.3.1"
|
||||
capabilities:
|
||||
provides_tools: []
|
||||
provides_hooks: []
|
||||
provides_middleware: []
|
||||
requires_env:
|
||||
- PPQ_API_KEY
|
||||
@@ -0,0 +1,18 @@
|
||||
# ppq-provider — catalog manifest. Pinned to the ppq-hermes-provider commit below.
|
||||
name: ppq
|
||||
repo: https://github.com/thepurpose-npub/ppq-hermes-provider
|
||||
sha: 94a6686fe4759d6fbd627a3ad58c9e1fcdb0b081
|
||||
subdir: model-providers/ppq
|
||||
description: "PayPerQ (ppq.ai) OpenAI-compatible model provider for Hermes — per-response cost estimation from ppq's published rate card, chat model discovery from GET /v1/models, automatic per-request Zero Data Retention opt-in, and a 3-layer picker pin strategy (user-local pins file → live top chat models from ppq's public stats dashboard → generic static fallback; generic installs never get the author's personal pins). Disclosure — model provider; PPQ_API_KEY and all prompts, tool schemas and responses go to ppq.ai (PayPerQ; terms https://ppq.ai/terms, contact matt@ppq.ai), a relay that routes requests to third-party inference partners, some outside the user's jurisdiction, and frontier providers still see prompts; usage is billed per request from the user's prepaid PayPerQ balance (funded by card or cryptocurrency on ppq.ai; the plugin itself makes no payments). Privacy protections are opt-in per request: for models badged privacyLevel 'zdr' the plugin automatically sends provider={\"zdr\": true, \"data_collection\": \"deny\"} so requests route only to endpoints with a Zero Data Retention policy that do not collect data (the zdr model set refreshes hourly from an unauthenticated GET /v1/models with a pinned fallback); models badged 'e2e' run inside TEE enclaves with no opt-in flag needed — enclave coverage applies to chat by default, not to image/video/audio, and true end-to-end encryption is only available via the optional local ppq-privacy-verifier proxy. Building the model picker, for any provider, starts a background unauthenticated POST to stats.ppq.ai at most hourly to fetch the top chat models; cost estimates and personal picker pins read optional local files under HERMES_HOME/plugin-data/ppq/ (prices.json, pins.json) that the plugin does not create, so costs show as unknown without a price snapshot. Additional caveats: Claude Opus 4.8 with web search enabled drops the ZDR guarantee, and some Anthropic/Gemini models may override the provider routing fields (order/only/ignore)."
|
||||
maintainer: thepurpose-npub
|
||||
tier: community
|
||||
category: models
|
||||
requires_hermes: ">=0.21.4"
|
||||
docs_url: https://github.com/thepurpose-npub/ppq-hermes-provider#readme
|
||||
version: "0.3.1"
|
||||
capabilities:
|
||||
provides_tools: []
|
||||
provides_hooks: []
|
||||
provides_middleware: []
|
||||
requires_env:
|
||||
- PPQ_API_KEY
|
||||
Reference in new issue
Block a user