The agent that grows with you
Python aiai-agentai-agentsanthropicchatgptclaudeclaude-codecodexhermeshermes-agentllmnous-researchopenai
feat(plugin-catalog): bump hermes-adaptive-effort to 0.4.0
Alexandre Tostivintd6ba56d63cfd
diff --git a/plugin-catalog/hermes-adaptive-effort.yaml b/plugin-catalog/hermes-adaptive-effort.yamlindex d8a301531ea..fdd0abeeef7 100644--- a/plugin-catalog/hermes-adaptive-effort.yaml+++ b/plugin-catalog/hermes-adaptive-effort.yaml@@ -1,27 +1,26 @@-# Draft for NousResearch/hermes-agent/plugin-catalog/hermes-adaptive-effort.yaml-# Pinned to master after the v0.3.1 pre-release (repository-root payload, so no subdir).-# The plugin payload is identical to v0.3.1; the pin adds the README screenshots and release tooling.+# Pinned to the v0.4.0 tag commit (repository-root payload, so no subdir).# Update sha and version together for later releases; a bump is a new catalog PR.name: hermes-adaptive-effortrepo: https://github.com/atostivint/hermes-adaptive-effort-sha: 0998a083d85ea52fbef38427b44a54d27332358a-description: "Choose a separate scorer to set the reasoning effort of each Hermes request. Disclosure — off by default; when a mode is enabled (or on an explicit `/hae probe`), sends the latest user message (or the parent-written subagent goal), truncated to 4000 characters, plus any configured guidance to the scorer you select (TypeSafe Jev at api.typesafe.ai by default, or OpenAI Decisions, OpenRouter, Cloudflare Workers AI, or a custom URL) using that service's key; in Hermes Desktop it also sets the focused chat's session reasoning selector through the gateway `config.set` API after each applied change, and it keeps a prompt-free effort-change history (64 changes × 64 conversations) in its plugin data directory."+sha: c84f1389670cdd5ec4607b13bd32c4809878c415+description: "Choose a separate scorer to set the reasoning effort of each Hermes request. Disclosure — off by default; when a mode is enabled (or on an explicit `/hae probe`), sends the latest user message (or the parent-written subagent goal), truncated to 4000 characters, plus any configured guidance to the scorer you select (TypeSafe Jev at api.typesafe.ai by default, or OpenAI Decisions, OpenRouter, Cloudflare Workers AI, Nace at console.nace.ai, or a custom URL) using that service's key; opt-in settings can also send the target model identity, up to 6 earlier user/assistant text messages (1200 characters each) and a separate continuation question to the same scorer; in Hermes Desktop it also sets the focused chat's session reasoning selector through the gateway `config.set` API after each applied change, and it keeps a prompt-free effort-change history (64 changes × 64 conversations) and per-route cache verdicts built from provider token counters (at most 128 routes) in its plugin data directory."maintainer: atostivinttier: communitycategory: modelsrequires_hermes: ">=0.21.6"-docs_url: https://github.com/atostivint/hermes-adaptive-effort/blob/0998a083d85ea52fbef38427b44a54d27332358a/docs/README.md-version: "0.3.1"+docs_url: https://github.com/atostivint/hermes-adaptive-effort/blob/c84f1389670cdd5ec4607b13bd32c4809878c415/docs/README.md+version: "0.4.0"readme: truescreenshots:- - https://raw.githubusercontent.com/atostivint/hermes-adaptive-effort/0998a083d85ea52fbef38427b44a54d27332358a/docs/images/desktop-routing-mode.png- - https://raw.githubusercontent.com/atostivint/hermes-adaptive-effort/0998a083d85ea52fbef38427b44a54d27332358a/docs/images/desktop-route-and-scorer.png- - https://raw.githubusercontent.com/atostivint/hermes-adaptive-effort/0998a083d85ea52fbef38427b44a54d27332358a/docs/images/desktop-settings.png- - https://raw.githubusercontent.com/atostivint/hermes-adaptive-effort/0998a083d85ea52fbef38427b44a54d27332358a/docs/images/routing-mode-popover.png+ - https://raw.githubusercontent.com/atostivint/hermes-adaptive-effort/c84f1389670cdd5ec4607b13bd32c4809878c415/docs/images/desktop-routing-mode.png+ - https://raw.githubusercontent.com/atostivint/hermes-adaptive-effort/c84f1389670cdd5ec4607b13bd32c4809878c415/docs/images/desktop-route-and-scorer.png+ - https://raw.githubusercontent.com/atostivint/hermes-adaptive-effort/c84f1389670cdd5ec4607b13bd32c4809878c415/docs/images/desktop-settings.png+ - https://raw.githubusercontent.com/atostivint/hermes-adaptive-effort/c84f1389670cdd5ec4607b13bd32c4809878c415/docs/images/routing-mode-popover.pngplatforms: []title: Hermes Adaptive Effortknown_issues:- "Pre-release: live effort acceptance is only partially validated; see the v0.3.0 release notes for the per-route evidence."+ - "0.4.0 removes the custom `chat_completions` scorer format and OpenRouter chat-model scoring; such configurations fail open (effort unchanged) until moved to a `systemone` endpoint or an OpenRouter decision model."capabilities:provides_tools: []provides_hooks:@@ -30,6 +29,8 @@ capabilities:- on_session_reset- subagent_start- subagent_stop+ - post_api_request+ - api_request_errorprovides_middleware:- llm_request# Provider credentials are conditional on the selected scorer, so none is