docs: deep audit — registry drift, stale claims, 2-week PR coverage, dashboard screenshot (#40952)

Full-corpus correctness audit of the hand-written docs against the codebase,
plus a 2-week merged-PR coverage sweep and one live dashboard screenshot.

Correctness (verified against COMMAND_REGISTRY / PROVIDER_REGISTRY / TOOLSETS /
tools.registry / DEFAULT_CONFIG / source):
- reference: add /version slash command, context_engine toolset, openai-api +
  novita-ai to --provider; fix tool count 64->71; model_catalog ttl 24->1;
  add profile describe to summary table; add real provider env vars
  (LM_API_KEY/LM_BASE_URL, KIMI_CODING_API_KEY, ALIBABA_CODING_PLAN_*,
  ANTHROPIC_BASE_URL, COPILOT_API_BASE_URL); fix faq "Windows: not natively".
- user-guide: fix broken `hermes -w -q` (->-z) and `hermes logs --tail` (->-f);
  language list 8->16; aux slots 8->11; docker separate-dashboard claim;
  _SECURITY_ARGS -> _BASE_SECURITY_ARGS.
- features: curator prune_builtins truth + missing CLI verbs; codex-runtime aux
  keys (context_compression->compression, vision_detect->vision); kanban
  terminate endpoint + promote/reassign/schedule/diagnostics/edit + per-profile
  cap; mcp mTLS (client_cert/client_key); built-in-plugins nemo_relay +
  teams_pipeline; api-server run approval endpoint; computer-use frontmatter.
- features N-Z + integrations: StepFun step-3-mini->step-3.5-flash; web-search
  backends 4->8; tool-gateway image-model IDs; voice-mode STT/TTS enums; remove
  phantom `rl` toolset; nous-portal status subcommand.
- messaging: WeCom typing/streaming cols; telegram transport default edit->auto;
  sms host default; simplex/ntfy `gateway setup` + pairing approve; line
  smart-chunking; matrix MATRIX_DM_AUTO_THREAD.
- developer-guide: build-a-plugin code examples (register_command signature,
  ContextEngine/ImageGenProvider/MemoryProvider ABCs); model-provider-plugin
  entry-point group hermes.plugins->hermes_agent.plugins; PLUGIN.yaml->plugin.yaml;
  agent-loop stale LOC; web-search-provider phantom crawl().

PR coverage (2-week window, 149 feat PRs):
- desktop.md refreshed for ~15 shipped features (zh-Hans switcher, rebindable
  shortcuts + zoom + Cmd+K, status-bar model picker + YOLO toggle, session-by-id
  + archive, multi-profile concurrent + cross-profile @session, composer history,
  Providers pane, per-profile remote hosts, Grok OAuth, aux-pin warning).
- configuration.md gateway-streaming default corrected to per-platform.
- tool-gateway.md free tool pool entitlement note.

Media:
- New /img/dashboard/admin-config.png — live dashboard Config admin page
  (captured from a clean profile, no secrets/personalization).
This commit is contained in:
Teknium
2026-06-07 01:39:06 -07:00
committed by GitHub
parent 3289d4adf2
commit 2d099fed1e
44 changed files with 202 additions and 62 deletions
@@ -49,7 +49,7 @@ Pick a model, hit **Switch**, and Hermes writes it to `~/.hermes/config.yaml` un
## Setting auxiliary models
Click **Show auxiliary** to reveal the eight task slots:
Click **Show auxiliary** to reveal the 11 task slots:
![Auxiliary panel expanded](/img/docs/dashboard-models/auxiliary-expanded.png)
@@ -66,6 +66,10 @@ Every auxiliary task defaults to `auto` — meaning Hermes uses your main model
| **Web Extract** | When you use `web_extract` heavily. Same logic as compression — summarization doesn't need reasoning. |
| **Skills Hub** | `hermes skills search` uses this. Usually fine at `auto`. |
| **MCP** | MCP tool routing. Usually fine at `auto`. |
| **Triage Specifier** | Routes the Kanban triage specifier (`hermes kanban specify`) that expands a rough one-liner into a concrete spec. A cheap, capable model works well. |
| **Kanban Decomposer** | Routes Kanban task decomposition — splits a triage task into a graph of child tasks for specialist profiles. |
| **Profile Describer** | Routes profile-description generation (`hermes profile describe --auto` / the dashboard auto-generate button). Short, cheap call. |
| **Curator** | Routes the curator skill-usage review pass. Can run for minutes on reasoning models, so a cheaper aux model is often worthwhile. |
### Per-task override
@@ -84,7 +88,7 @@ Every model card on the page has a **Use as** dropdown. This is the fast path
The dropdown has:
- **Main model** — same as clicking Change on the main row.
- **All auxiliary tasks** — assigns this model to all 8 aux slots at once. Useful when you just want every side-job on a cheap flash model.
- **All auxiliary tasks** — assigns this model to all 11 aux slots at once. Useful when you just want every side-job on a cheap flash model.
- **Individual task options** — Vision, Web Extract, Compression, etc. The currently-assigned model for each task is marked `current`.
Cards are badged with `main` or `aux · <task>` when they're currently assigned to something — so you can see at a glance which of your historical models are wired in where.