2efa4f3caa
Three shared-metrics counters that answer "which models misbehave, frustrate
users, or run out of room", all attributed to catalog provider/model names
(custom endpoints and loopback servers collapse to custom) and all behind the
existing enabled() gate.
hermes.model_tool_quality.count {provider, model, call_role, issue}
Counts every tool call a model emits where the agent validates it, clean calls
as issue=none so the rates have a denominator: invalid_json, unknown_tool,
schema_mismatch (missing required keys / non-object), empty_arguments (only for
tools with required params), repaired (Hermes fixed the name or the streamed
argument JSON and ran the call). Stream assembly marks args it repaired and the
chat transport carries the marker onto the normalized ToolCall, because
normalization otherwise erases it.
hermes.model_friction.count {provider, model, signal}
retry / undo / interrupt / quick_abandon / switch_away, blamed on the model that
produced the turn: the relay session remembers its last primary route, so a
/retry after a /model switch still counts against the retried model. Counted
where the action executes, once: CLI handlers (skipped on the TUI slash worker's
shadow CLI), tui_gateway command.dispatch retry/undo and session.undo (Ink
/retry now sends intent=retry, so it counts as a retry, not an undo), gateway
/retry and /undo (multiplexed runners bind the owning profile home), and every
/model surface via record_model_switch(from_model=...). Interrupts and quick
abandonment (session closed within 60s of a failed turn) come from the runtime's
turn close, for attended entrypoints only; a turn still running when the
session closes is neither.
hermes.context_peak.count {provider, model, peak_fill_bucket, window_bucket, limit_hit}
One row per closed top-level session: the fullest primary context it reached
(post_api_request now carries the compressor's context_length) and whether a
call was rejected as too large (context_overflow / payload_too_large, the
rejections Hermes answers with a forced compression). A session whose every
call overflowed still reports, with unknown buckets.
Website
This website is built using Docusaurus, a modern static website generator.
Reading the docs on GitHub? The Markdown under
docs/is authored for the rendered site at https://hermes-agent.nousresearch.com/docs/. Cross-page links are relative Markdown paths, so they follow through on GitHub's file viewer too. Every page on the site has an Edit this page link that opens the source file here.
Authoring links in docs/
- Link to another page with a relative Markdown path, anchors included:
[Profiles](../user-guide/profiles.md),[Bundles](../user-guide/features/skills.md#skill-bundles). Docusaurus turns the file path into the page route; GitHub follows the same path. Site routes (/user-guide/profiles,/docs/user-guide/profiles) only work on the rendered site — GitHub resolves them as repository paths and 404s, and the/docs/form also emits/docs/zh-Hans/docs/...404s in the zh-Hans build becausebaseUrlis already/docs/. python3 website/scripts/check_doc_links.pyfails on any route-style link in hand-authored pages (EN and the zh-Hans mirror);--fixrewrites them. It runs in theDocs Site Checksworkflow. Generated pages (user-guide/skills/{bundled,optional},reference/*skills-catalog.md) are produced byscripts/generate-skill-docs.py, which emits the same relative form.- Pin
{#anchor}on cross-linked headings so the zh-Hans mirror keeps the same id.
Installation
yarn
Local Development
yarn start
This command starts a local development server and opens up a browser window. Most changes are reflected live without having to restart the server.
Build
yarn build
This command generates static content into the build directory and can be served using any static contents hosting service.
Deployment
Using SSH:
USE_SSH=true yarn deploy
Not using SSH:
GIT_USER=<Your GitHub username> yarn deploy
If you are using GitHub pages for hosting, this command is a convenient way to build the website and push to the gh-pages branch.
Diagram Linting
CI runs ascii-guard to lint docs for ASCII box diagrams. Use Mermaid (````mermaid`) or plain lists/tables instead of ASCII boxes to avoid CI failures.