From d15208e5f0eaf937e8692301fa89c38f29804b34 Mon Sep 17 00:00:00 2001 From: teknium1 <127238744+teknium1@users.noreply.github.com> Date: Fri, 18 Sep 2026 11:20:15 -0700 Subject: [PATCH] docs(website): re-run the link sweep over pages merged since the rebase `python3 website/scripts/check_doc_links.py --fix` over the current tree: 126 route-style links in 9 pages (the six that conflicted with #114784/#114806/ #114851 plus google-gemini, cron and secrets) rewritten to relative file paths. Check mode is clean afterwards. --- website/docs/guides/google-gemini.md | 2 +- .../guides/run-hermes-with-nous-portal.md | 30 ++++---- website/docs/integrations/nous-portal.md | 26 +++---- website/docs/reference/slash-commands.md | 48 ++++++------- website/docs/user-guide/configuration.md | 72 +++++++++---------- website/docs/user-guide/features/cron.md | 2 +- website/docs/user-guide/secrets/index.md | 2 +- .../guides/run-hermes-with-nous-portal.md | 30 ++++---- .../current/integrations/nous-portal.md | 26 +++---- 9 files changed, 119 insertions(+), 119 deletions(-) diff --git a/website/docs/guides/google-gemini.md b/website/docs/guides/google-gemini.md index 064e202033..f90c00ed2b 100644 --- a/website/docs/guides/google-gemini.md +++ b/website/docs/guides/google-gemini.md @@ -124,7 +124,7 @@ express-mode** keys start with `AQ.…` and only authenticate against `GEMINI_BASE_URL` to `https://aiplatform.googleapis.com` (with or without `/v1beta1`) Hermes completes it to the `publishers/google` form; a base URL on any other host (a proxy) is never rewritten. Express keys are separate from the OAuth-based -[Vertex AI provider](/guides/google-vertex), which needs no API key. +[Vertex AI provider](./google-vertex.md), which needs no API key. ## Available Models diff --git a/website/docs/guides/run-hermes-with-nous-portal.md b/website/docs/guides/run-hermes-with-nous-portal.md index b100f1592b..75ecba41d2 100644 --- a/website/docs/guides/run-hermes-with-nous-portal.md +++ b/website/docs/guides/run-hermes-with-nous-portal.md @@ -6,12 +6,12 @@ description: "Start-to-finish walkthrough: subscribe, set up, switch models, ena # Run Hermes Agent with Nous Portal -This guide walks you through running Hermes Agent on a [Nous Portal](https://portal.nousresearch.com) subscription end to end — from signing up to verifying that every tool routes correctly. If you just want the overview of what the Portal is and what's in the subscription, see the [Nous Portal integration page](/integrations/nous-portal). This page is the task script. +This guide walks you through running Hermes Agent on a [Nous Portal](https://portal.nousresearch.com) subscription end to end — from signing up to verifying that every tool routes correctly. If you just want the overview of what the Portal is and what's in the subscription, see the [Nous Portal integration page](../integrations/nous-portal.md). This page is the task script. ## Prerequisites -- Hermes Agent installed ([Quickstart](/getting-started/quickstart)) -- A web browser on the machine you're setting up (or SSH port forwarding — see [OAuth over SSH](/guides/oauth-over-ssh)) +- Hermes Agent installed ([Quickstart](../getting-started/quickstart.md)) +- A web browser on the machine you're setting up (or SSH port forwarding — see [OAuth over SSH](./oauth-over-ssh.md)) - About 5 minutes You do **not** need: an OpenAI key, an Anthropic key, a Firecrawl account, a FAL account, a Browser Use account, or any other per-vendor credential. That's the whole point. @@ -52,7 +52,7 @@ hermes auth add nous --type oauth # Then re-run `hermes setup --portal` to wire the provider + gateway ``` -See [OAuth over SSH / Remote Hosts](/guides/oauth-over-ssh) for the full walkthrough including ProxyJump chains, mosh/tmux, and ControlMaster gotchas. +See [OAuth over SSH / Remote Hosts](./oauth-over-ssh.md) for the full walkthrough including ProxyJump chains, mosh/tmux, and ControlMaster gotchas. ## 3. Verify it worked @@ -120,7 +120,7 @@ hermes config set model.default anthropic/claude-sonnet-4.6 ### Don't pick Hermes-4 for agent work -Hermes-4-70B and Hermes-4-405B are available on the Portal at deep discounts, but they're **chat/reasoning models**, not tool-call-tuned. They will struggle with multi-step agent loops. Use them for conversation/research work through the [subscription proxy](/user-guide/features/subscription-proxy) from non-agent tools. For Hermes Agent itself, stick to the frontier agentic models above. +Hermes-4-70B and Hermes-4-405B are available on the Portal at deep discounts, but they're **chat/reasoning models**, not tool-call-tuned. They will struggle with multi-step agent loops. Use them for conversation/research work through the [subscription proxy](../user-guide/features/subscription-proxy.md) from non-agent tools. For Hermes Agent itself, stick to the frontier agentic models above. The Portal's own [info page](https://portal.nousresearch.com/info) carries this warning too — it's the official Nous guidance, not just a Hermes-side opinion. @@ -148,7 +148,7 @@ You'll see per-tool routing — `via Nous Portal` for the ones routed through th ## 7. (Optional) Enable voice mode -Because the Tool Gateway includes OpenAI TTS, [voice mode](/user-guide/features/voice-mode) works without a separate OpenAI key: +Because the Tool Gateway includes OpenAI TTS, [voice mode](../user-guide/features/voice-mode.md) works without a separate OpenAI key: ```bash hermes setup tts @@ -160,7 +160,7 @@ Then in any messaging-platform session (Telegram, Discord, Signal, etc.), send a ## 8. (Optional) Cron + always-on workflows -The Portal subscription works for [cron jobs](/user-guide/features/cron) and [batch processing](/user-guide/features/batch-processing) the same way it works for interactive chat — the OAuth refresh token is reused automatically. No additional setup; just schedule cron jobs and they'll bill against your subscription. +The Portal subscription works for [cron jobs](../user-guide/features/cron.md) and [batch processing](../user-guide/features/batch-processing.md) the same way it works for interactive chat — the OAuth refresh token is reused automatically. No additional setup; just schedule cron jobs and they'll bill against your subscription. ```bash hermes cron create "0 9 * * *" \ @@ -172,7 +172,7 @@ The cron job runs unattended, calls the model + web search + summarization all t ## Profiles and multi-user setups -If you use [Hermes profiles](/user-guide/profiles) (e.g. a separate config per project), each profile is an independent credential island: a profile that has never signed in to the Portal fails closed instead of adopting another profile's session. Sign in once per profile with `hermes -p portal` — when a shared Portal session already exists on the machine it offers to import it without a browser round-trip, and from then on the shared token store keeps that profile's token current. See [Profile setup](/integrations/nous-portal#profile-setup). +If you use [Hermes profiles](../user-guide/profiles.md) (e.g. a separate config per project), each profile is an independent credential island: a profile that has never signed in to the Portal fails closed instead of adopting another profile's session. Sign in once per profile with `hermes -p portal` — when a shared Portal session already exists on the machine it offers to import it without a browser round-trip, and from then on the shared token store keeps that profile's token current. See [Profile setup](../integrations/nous-portal.md#profile-setup). For team setups where multiple humans share a machine, each human has their own Portal account → each home directory holds its own `~/.hermes/auth.json` → no token sharing across users. This is the right boundary. @@ -186,7 +186,7 @@ The OAuth flow didn't complete. Re-run it: hermes portal ``` -If your browser doesn't open or the callback fails, you're likely on a remote/headless host — see [OAuth over SSH](/guides/oauth-over-ssh) for the port-forwarding workarounds. +If your browser doesn't open or the callback fails, you're likely on a remote/headless host — see [OAuth over SSH](./oauth-over-ssh.md) for the port-forwarding workarounds. ### "Model: currently openrouter" (or some other provider) instead of "using Nous as inference provider" @@ -268,9 +268,9 @@ That's the deal. If you're using more than two of those backends anyway, the sub ## See also -- **[Nous Portal integration page](/integrations/nous-portal)** — Overview of what's in the subscription -- **[Tool Gateway](/user-guide/features/tool-gateway)** — Full details on every gateway-routed tool -- **[Subscription proxy](/user-guide/features/subscription-proxy)** — Use your Portal subscription from non-Hermes tools -- **[Voice mode](/user-guide/features/voice-mode)** — Set up voice conversations on the Portal subscription -- **[OAuth over SSH](/guides/oauth-over-ssh)** — Remote / headless login patterns -- **[Profiles](/user-guide/profiles)** — Share one Portal login across multiple Hermes configurations +- **[Nous Portal integration page](../integrations/nous-portal.md)** — Overview of what's in the subscription +- **[Tool Gateway](../user-guide/features/tool-gateway.md)** — Full details on every gateway-routed tool +- **[Subscription proxy](../user-guide/features/subscription-proxy.md)** — Use your Portal subscription from non-Hermes tools +- **[Voice mode](../user-guide/features/voice-mode.md)** — Set up voice conversations on the Portal subscription +- **[OAuth over SSH](./oauth-over-ssh.md)** — Remote / headless login patterns +- **[Profiles](../user-guide/profiles.md)** — Share one Portal login across multiple Hermes configurations diff --git a/website/docs/integrations/nous-portal.md b/website/docs/integrations/nous-portal.md index c0095af0bf..9cc2feb5bc 100644 --- a/website/docs/integrations/nous-portal.md +++ b/website/docs/integrations/nous-portal.md @@ -50,13 +50,13 @@ Because routing is per-model and not always through OpenRouter, OpenRouter-speci ### The Nous Tool Gateway -The same subscription unlocks the [Tool Gateway](/user-guide/features/tool-gateway), which routes Hermes Agent's tool calls through Nous-managed infrastructure. Five backends, one login: +The same subscription unlocks the [Tool Gateway](../user-guide/features/tool-gateway.md), which routes Hermes Agent's tool calls through Nous-managed infrastructure. Five backends, one login: | Tool | Partner | What it does | |------|---------|--------------| | **Web search & extract** | Firecrawl | Agent-grade search and full-page extraction. No Firecrawl API key, no rate limit babysitting. | | **Image generation** | FAL | Nine models under one endpoint: FLUX 2 Klein 9B, FLUX 2 Pro, Z-Image Turbo, Nano Banana Pro (Gemini 3 Pro Image), GPT Image 1.5, GPT Image 2, Ideogram V3, Recraft V4 Pro, Qwen Image. | -| **Text-to-speech** | OpenAI TTS | High-quality TTS without a separate OpenAI key. Enables [voice mode](/user-guide/features/voice-mode) across messaging platforms. | +| **Text-to-speech** | OpenAI TTS | High-quality TTS without a separate OpenAI key. Enables [voice mode](../user-guide/features/voice-mode.md) across messaging platforms. | | **Cloud browser automation** | Browser Use | Headless Chromium sessions for `browser_navigate`, `browser_click`, `browser_type`, `browser_vision`. No Browserbase account needed. | | **Cloud terminal sandbox** | Modal | Serverless terminal sandboxes for code execution (optional add-on). | @@ -70,13 +70,13 @@ Because everything routes through one OAuth-authenticated Portal session, you do ### Cross-platform parity -[Native Windows](/user-guide/windows-native) makes per-tool API key setup its rough edge — installing a Firecrawl account, a FAL account, a Browser Use account, an OpenAI key from Windows is the highest-friction part of getting a useful agent. A Portal subscription smooths that out: one OAuth covers the model and every gateway tool, so Windows users get the same experience as macOS/Linux without manually configuring four backends. +[Native Windows](../user-guide/windows-native.md) makes per-tool API key setup its rough edge — installing a Firecrawl account, a FAL account, a Browser Use account, an OpenAI key from Windows is the highest-friction part of getting a useful agent. A Portal subscription smooths that out: one OAuth covers the model and every gateway tool, so Windows users get the same experience as macOS/Linux without manually configuring four backends. ## A note on Hermes 4 Nous Research's own **Hermes 4** family (Hermes-4-70B, Hermes-4-405B) is available through the Portal at heavily discounted rates. These are **frontier hybrid-reasoning chat models** — strong at math, science, instruction following, schema adherence, roleplay, and long-form writing. -They are **not recommended for use inside Hermes Agent**, however. Hermes 4 is tuned for chat and reasoning, not the rapid-fire tool-calling loop the agent relies on. Use them for research workflows or via the [subscription proxy](/user-guide/features/subscription-proxy) from other tooling — but for agent work, pick a frontier agentic model from the catalog instead: +They are **not recommended for use inside Hermes Agent**, however. Hermes 4 is tuned for chat and reasoning, not the rapid-fire tool-calling loop the agent relies on. Use them for research workflows or via the [subscription proxy](../user-guide/features/subscription-proxy.md) from other tooling — but for agent work, pick a frontier agentic model from the catalog instead: ```bash /model anthropic/claude-sonnet-4.6 # best general-purpose agentic model @@ -120,11 +120,11 @@ Your existing providers stay configured. You can switch between them with `/mode ### Headless / SSH / remote setup -OAuth needs a browser, but the loopback callback runs on the machine where Hermes is running. For remote hosts, see [OAuth over SSH / Remote Hosts](/guides/oauth-over-ssh) — the same patterns work for the Portal as for any other OAuth-based provider (`ssh -L` port forwarding). +OAuth needs a browser, but the loopback callback runs on the machine where Hermes is running. For remote hosts, see [OAuth over SSH / Remote Hosts](../guides/oauth-over-ssh.md) — the same patterns work for the Portal as for any other OAuth-based provider (`ssh -L` port forwarding). ### Profile setup {#profile-setup} -If you use [Hermes profiles](/user-guide/profiles), the Portal refresh token is shared across profiles via a shared token store — but the store **refreshes an existing login, it does not create one**. Profiles are independent islands ([#111724](https://github.com/NousResearch/hermes-agent/issues/111724)), so a profile that has never signed in to the Portal has no Nous credentials of its own: at boot it fails closed with `Profile '' is not connected to any AI provider yet` rather than silently adopting another profile's session. +If you use [Hermes profiles](../user-guide/profiles.md), the Portal refresh token is shared across profiles via a shared token store — but the store **refreshes an existing login, it does not create one**. Profiles are independent islands ([#111724](https://github.com/NousResearch/hermes-agent/issues/111724)), so a profile that has never signed in to the Portal has no Nous credentials of its own: at boot it fails closed with `Profile '' is not connected to any AI provider yet` rather than silently adopting another profile's session. Sign in **once per profile** with `hermes -p portal` (alias for `hermes -p auth add nous --type oauth`). When a shared Portal session already exists on the machine, that command offers to import it — one confirmation, no browser round-trip. After that first import the profile keeps its own state, and the shared store keeps its token current whenever any profile refreshes or re-logs in. `hermes profile create --clone-all` from a signed-in profile also carries the Portal login (only single-use grants such as Anthropic/Codex are stripped from clones). @@ -195,7 +195,7 @@ hermes tools # → TTS → "Nous Subscription" ``` -The Tool Gateway is opt-in per tool, not all-or-nothing. The managed backends show up in `hermes tools` whether or not you're logged into Nous Portal — if you pick "Nous Subscription" before authenticating, Hermes runs the Portal login inline (it won't change your inference provider or touch your other tools). See the [Tool Gateway docs](/user-guide/features/tool-gateway) for the full per-tool configuration matrix. +The Tool Gateway is opt-in per tool, not all-or-nothing. The managed backends show up in `hermes tools` whether or not you're logged into Nous Portal — if you pick "Nous Subscription" before authenticating, Hermes runs the Portal login inline (it won't change your inference provider or touch your other tools). See the [Tool Gateway docs](../user-guide/features/tool-gateway.md) for the full per-tool configuration matrix. ### Subscription management @@ -280,9 +280,9 @@ Check `hermes portal info` first — if it shows you're using a different provid ## See also -- **[Tool Gateway](/user-guide/features/tool-gateway)** — Full details on every gateway tool, per-tool config, and pricing -- **[Subscription proxy](/user-guide/features/subscription-proxy)** — Use your Portal subscription from non-Hermes tools (other agents, scripts, third-party clients) -- **[Voice mode](/user-guide/features/voice-mode)** — Voice conversations using the Portal's OpenAI TTS -- **[AI Providers](/integrations/providers)** — Full provider catalog if you want to compare alternatives -- **[OAuth over SSH](/guides/oauth-over-ssh)** — Login from remote hosts or browser-only environments -- **[Profiles](/user-guide/profiles)** — Multiple Hermes configurations sharing one Portal login +- **[Tool Gateway](../user-guide/features/tool-gateway.md)** — Full details on every gateway tool, per-tool config, and pricing +- **[Subscription proxy](../user-guide/features/subscription-proxy.md)** — Use your Portal subscription from non-Hermes tools (other agents, scripts, third-party clients) +- **[Voice mode](../user-guide/features/voice-mode.md)** — Voice conversations using the Portal's OpenAI TTS +- **[AI Providers](./providers.md)** — Full provider catalog if you want to compare alternatives +- **[OAuth over SSH](../guides/oauth-over-ssh.md)** — Login from remote hosts or browser-only environments +- **[Profiles](../user-guide/profiles.md)** — Multiple Hermes configurations sharing one Portal login diff --git a/website/docs/reference/slash-commands.md b/website/docs/reference/slash-commands.md index 527735c827..1ecdcf5ab9 100644 --- a/website/docs/reference/slash-commands.md +++ b/website/docs/reference/slash-commands.md @@ -51,13 +51,13 @@ Type `/` in the CLI to open the autocomplete menu. Built-in commands are case-in | `/stop` | Kill all running background processes | | `/queue ` (alias: `/q`) | Queue a prompt for the next turn (doesn't interrupt the current agent response). In the CLI, `/queue` with no arguments lists the pending queue, and `/queue list`, `/queue edit N `, `/queue rm N`, `/queue move A B`, and `/queue clear` inspect and manage queued prompts before they are sent. Prompts that begin with a management word can be force-queued with `/queue add `. | | `/steer ` | Inject a mid-run note that arrives at the agent **after the next tool call** — no interrupt, no new user turn. The text is appended to the last tool result's content once the current tool completes, giving the agent new context without breaking the current tool-calling loop. Use this to nudge direction mid-task (e.g. "focus on the auth module" while the agent is running tests). | -| `/goal ` | Set a standing goal Hermes works toward across turns — our take on the Ralph loop. After each turn an auxiliary judge model decides whether the goal is done; if not, Hermes auto-continues. Subcommands: `/goal status`, `/goal pause`, `/goal resume`, `/goal clear`. Budget defaults to 20 turns (`goals.max_turns`); any real user message preempts the continuation loop, and state survives `/resume`. See [Persistent Goals](/user-guide/features/goals) for the full walkthrough. | +| `/goal ` | Set a standing goal Hermes works toward across turns — our take on the Ralph loop. After each turn an auxiliary judge model decides whether the goal is done; if not, Hermes auto-continues. Subcommands: `/goal status`, `/goal pause`, `/goal resume`, `/goal clear`. Budget defaults to 20 turns (`goals.max_turns`); any real user message preempts the continuation loop, and state survives `/resume`. See [Persistent Goals](../user-guide/features/goals.md) for the full walkthrough. | | `/subgoal ` | Append a user-supplied criterion to the active goal mid-loop. The continuation prompt surfaces all subgoals to the agent verbatim, and the judge factors them into its DONE/CONTINUE verdict — so the goal isn't marked done until the original goal **and** every subgoal are met. Subcommands: `/subgoal` (list), `/subgoal remove `, `/subgoal clear`. Requires an active `/goal`. | -| `/heartbeat every ` (alias: `/hb`) | Set a recurring prompt that re-enters **this session** as a normal user turn whenever it's idle and the interval has elapsed (min 60s; missed ticks coalesce). Subcommands: `/heartbeat status`, `/heartbeat pause`, `/heartbeat resume`, `/heartbeat clear`. Session-scoped and in-process — use `hermes cron` for durable isolated schedules. See [Session Heartbeats](/user-guide/features/heartbeat). | -| `/loop [interval] [--times N] [--until ]` (alias: `/proactive`) | Re-run a prompt (or another slash command) on a recurring interval in **this session** — fixed cadence (`/loop 5m check the deploy`) or continuous re-fire when no interval is given. `--times N` caps the run count; `--until ` lets an auxiliary judge stop the loop when the condition is met. Subcommands: `/loop status`, `/loop pause`, `/loop resume`, `/loop stop`. See [Loops](/user-guide/features/loops). | +| `/heartbeat every ` (alias: `/hb`) | Set a recurring prompt that re-enters **this session** as a normal user turn whenever it's idle and the interval has elapsed (min 60s; missed ticks coalesce). Subcommands: `/heartbeat status`, `/heartbeat pause`, `/heartbeat resume`, `/heartbeat clear`. Session-scoped and in-process — use `hermes cron` for durable isolated schedules. See [Session Heartbeats](../user-guide/features/heartbeat.md). | +| `/loop [interval] [--times N] [--until ]` (alias: `/proactive`) | Re-run a prompt (or another slash command) on a recurring interval in **this session** — fixed cadence (`/loop 5m check the deploy`) or continuous re-fire when no interval is given. `--times N` caps the run count; `--until ` lets an auxiliary judge stop the loop when the condition is met. Subcommands: `/loop status`, `/loop pause`, `/loop resume`, `/loop stop`. See [Loops](../user-guide/features/loops.md). | | `/refine [focus]` | Run the background memory/skill self-improvement review **now** instead of waiting for the automatic post-turn trigger. Optional focus text steers the review (e.g. `/refine save the deploy workflow as a skill`). Runs in a background fork against a conversation snapshot — the live session and prompt cache are untouched; results are reported when done. | -| `/review [instructions]` | Spawn an independent, full-privilege reviewer subagent to review the work just discussed — a PR, code, docs, any artifact referenced in the last 10 chat messages. It investigates in the background (opens the PR, reads the diff, runs code) and its full review re-enters this session as a background-subagent completion the primary agent can act on. Pin a dedicated review model via `auxiliary.review` in config.yaml (defaults to your main model). See [Subagent Delegation](/user-guide/features/delegation#the-review-command). | -| `/moa ` | Run a single prompt through the default [Mixture of Agents](/user-guide/features/mixture-of-agents) preset, then restore your current model. One-shot — does not change your session model. | +| `/review [instructions]` | Spawn an independent, full-privilege reviewer subagent to review the work just discussed — a PR, code, docs, any artifact referenced in the last 10 chat messages. It investigates in the background (opens the PR, reads the diff, runs code) and its full review re-enters this session as a background-subagent completion the primary agent can act on. Pin a dedicated review model via `auxiliary.review` in config.yaml (defaults to your main model). See [Subagent Delegation](../user-guide/features/delegation.md#the-review-command). | +| `/moa ` | Run a single prompt through the default [Mixture of Agents](../user-guide/features/mixture-of-agents.md) preset, then restore your current model. One-shot — does not change your session model. | | `/resume [name]` | Resume a previously-named session. Bare `/resume` lists this chat's named sessions ranked by most recent activity (a long-running conversation that compression has rotated several times counts as one entry, shown at its live tip). In the classic CLI this (and `/sessions `) is refused while a turn is running — the CLI shares one agent across sessions, so switching mid-turn would file the rest of the running turn under the other session. | | `/sessions` (TUI alias: `/switch`) | Classic CLI: browse and resume previous sessions in an interactive picker. TUI: open the live session switcher for currently open TUI sessions. Use `/sessions new` in the TUI to start another live session immediately. | | `/egress [status]` | Show Docker egress proxy status — enabled/configured/running state, credential source, token mappings, uncovered providers, and next remediation step. Works in CLI, TUI, Desktop chat, and messaging gateway. | @@ -65,12 +65,12 @@ Type `/` in the CLI to open the autocomplete menu. Built-in commands are case-in | `/status` | Show session info — model, provider, profile, session ID, working directory, title, created/updated timestamps, token totals, agent-running state — followed by a local **Session recap** block (recent user/assistant turn counts, tool result count, top tools used, last few files touched, the latest user prompt, and the latest assistant reply). The recap is computed locally from the in-memory conversation; no LLM call, no prompt-cache impact. | | `/context [all]` (alias: `/ctx`) | Visual context-window breakdown. On the CLI/TUI: a 5×20 glyph block grid (each cell ≈ 1% of the model window) plus an estimated per-category table — system prompt, tool definitions, rules, skills index, MCP, subagents, memory, conversation — versus free space. On messaging platforms: a usage gauge with auto-compression threshold/headroom, compression stats, cumulative throughput, and the same category table in plain text. On the CLI, messaging platforms, and TUI/Desktop sessions on a compute host, the output ends with a per-file **Context files** listing (.hermes.md, AGENTS.md chain, CLAUDE.md, .cursorrules + .cursor/rules/*.mdc, SOUL.md) showing each file's token estimate and whether it was loaded, truncated over `context_file_max_chars`, shadowed by a higher-priority context type, blocked by the injection scan, empty/unreadable, or suppressed by the install-tree guard — the answer to "why is my CLAUDE.md ignored?". `/context all` appends per-skill and per-toolset cost listings (index cost vs SKILL.md load cost; schema tokens per toolset). Read-only and computed locally — no LLM call, no prompt-cache impact. | | `/agents` (alias: `/tasks`) | Show active agents and running tasks across the current session. | -| `/bg ` | Run a prompt in a separate background session. The agent processes your prompt independently — your current session stays free for other work. Results appear as a panel when the task finishes. See [CLI Background Sessions](/user-guide/cli#background-sessions). | +| `/bg ` | Run a prompt in a separate background session. The agent processes your prompt independently — your current session stays free for other work. Results appear as a panel when the task finishes. See [CLI Background Sessions](../user-guide/cli.md#background-sessions). | | `/btw ` | Ask a quick side question **about the current conversation** without interrupting it. A one-shot auxiliary LLM call answers from a read-only snapshot of the transcript — the live session's history and prompt cache are untouched, and the current turn keeps running. For independent work with a fresh context, use `/bg`. | | `/branch [name]` (alias: `/fork`) | Branch the current session (explore a different path). Classic CLI: refused mid-turn like `/handoff` — wait for the current response to finish, then retry. | -| `/worktree [new [name]\|list]` | **CLI only.** Inspect or create isolated git worktrees mid-session (inspired by Copilot CLI's `/worktree new`). Bare `/worktree` shows the active worktree; `/worktree list` lists the repo's worktrees; `/worktree new [name]` creates a worktree under `.worktrees/` (branched from the freshly-fetched remote tip, honoring `worktree_sync`) and retargets the session's terminal and file tools into it. Named trees use your name (`hermes/` branch); unnamed ones get a random `hermes-`. On exit the tree is kept only if it has unpushed commits — same lifecycle as `hermes -w`. See [Git Worktrees](/user-guide/git-worktrees). | -| `/handoff ` | **CLI only.** Hand the current session off to a messaging platform (Telegram, Discord, Slack, WhatsApp, Signal, Matrix). The gateway picks it up immediately, creates a fresh thread on platforms that support threads (Telegram topics, Discord text-channel threads, Slack and Matrix message-anchored threads), re-binds the destination to your CLI session_id so the full role-aware transcript replays, and forges a synthetic user turn so the agent confirms it's working in the new place. Your CLI exits cleanly on success with a `/resume` hint; resume locally any time with `/resume `. Refused mid-turn. Requires the gateway to be running and a home channel configured for the target platform (`/sethome` from the destination chat). See [Cross-Platform Handoff](/user-guide/sessions#cross-platform-handoff). | -| `/journey [list\|delete <id>\|edit <id>]` (aliases: `/learning`, `/memory-graph`) | Open the learning journey timeline of learned skills + memories. Works in the classic CLI, as a TUI overlay, and in the desktop app (Star Map panel). Not available on messaging platforms. See [Learning Journey](/user-guide/features/memory#learning-journey-journey). | +| `/worktree [new [name]\|list]` | **CLI only.** Inspect or create isolated git worktrees mid-session (inspired by Copilot CLI's `/worktree new`). Bare `/worktree` shows the active worktree; `/worktree list` lists the repo's worktrees; `/worktree new [name]` creates a worktree under `.worktrees/` (branched from the freshly-fetched remote tip, honoring `worktree_sync`) and retargets the session's terminal and file tools into it. Named trees use your name (`hermes/<name>` branch); unnamed ones get a random `hermes-<id>`. On exit the tree is kept only if it has unpushed commits — same lifecycle as `hermes -w`. See [Git Worktrees](../user-guide/git-worktrees.md). | +| `/handoff <platform>` | **CLI only.** Hand the current session off to a messaging platform (Telegram, Discord, Slack, WhatsApp, Signal, Matrix). The gateway picks it up immediately, creates a fresh thread on platforms that support threads (Telegram topics, Discord text-channel threads, Slack and Matrix message-anchored threads), re-binds the destination to your CLI session_id so the full role-aware transcript replays, and forges a synthetic user turn so the agent confirms it's working in the new place. Your CLI exits cleanly on success with a `/resume` hint; resume locally any time with `/resume <title>`. Refused mid-turn. Requires the gateway to be running and a home channel configured for the target platform (`/sethome` from the destination chat). See [Cross-Platform Handoff](../user-guide/sessions.md#cross-platform-handoff). | +| `/journey [list\|delete <id>\|edit <id>]` (aliases: `/learning`, `/memory-graph`) | Open the learning journey timeline of learned skills + memories. Works in the classic CLI, as a TUI overlay, and in the desktop app (Star Map panel). Not available on messaging platforms. See [Learning Journey](../user-guide/features/memory.md#learning-journey-journey). | ### Configuration @@ -105,23 +105,23 @@ Type `/` in the CLI to open the autocomplete menu. Built-in commands are case-in | `/tools [list\|disable\|enable] [name...]` | Manage tools: list available tools, or disable/enable specific tools for the current session. Disabling a tool removes it from the agent's toolset and triggers a session reset. | | `/toolsets` | List available toolsets | | `/browser [connect\|disconnect\|status]` | Manage a local Chromium-family CDP connection. `connect` attaches browser tools to a running Chrome, Brave, Chromium, or Edge instance (default: `http://127.0.0.1:9222`). `disconnect` detaches. `status` shows current connection. Auto-launches a supported Chromium-family browser if no debugger is detected. | -| `/skills` | Search, install, inspect, or manage skills from online registries. Also the review surface for the skill write-approval gate: `/skills pending`, `/skills diff <id>`, `/skills approve <id>`, `/skills reject <id>`, `/skills approval on\|off`. See [Gating agent skill writes](/user-guide/features/skills#gating-agent-skill-writes-skillswrite_approval). | -| `/memory [pending\|approve\|reject\|approval]` | Review pending memory writes staged by the write-approval gate (`memory.write_approval`) and toggle the gate. See [Controlling memory writes](/user-guide/features/memory#controlling-memory-writes-write_approval). | -| `/bundles` | List configured skill bundles — `/<name>` slash aliases that preload several skills at once. Configure under `bundles:` in `~/.hermes/config.yaml`. See [Skill Bundles](/user-guide/features/skills#skill-bundles). | +| `/skills` | Search, install, inspect, or manage skills from online registries. Also the review surface for the skill write-approval gate: `/skills pending`, `/skills diff <id>`, `/skills approve <id>`, `/skills reject <id>`, `/skills approval on\|off`. See [Gating agent skill writes](../user-guide/features/skills.md#gating-agent-skill-writes-skillswrite_approval). | +| `/memory [pending\|approve\|reject\|approval]` | Review pending memory writes staged by the write-approval gate (`memory.write_approval`) and toggle the gate. See [Controlling memory writes](../user-guide/features/memory.md#controlling-memory-writes-write_approval). | +| `/bundles` | List configured skill bundles — `/<name>` slash aliases that preload several skills at once. Configure under `bundles:` in `~/.hermes/config.yaml`. See [Skill Bundles](../user-guide/features/skills.md#skill-bundles). | | `/learn <what to learn from>` | Distill a reusable skill from anything you describe — a directory, a URL, the workflow you just walked the agent through, or pasted notes. Open-ended: the agent gathers the sources with its own tools and authors a `SKILL.md` following the house authoring standards. Works in the CLI, the messaging gateway, the TUI, and the dashboard Skills page. | | `/plan [task]` | Write a markdown implementation plan to `.hermes/plans/` in the active workspace — planning only, no execution. Empty argument infers the task from the conversation. (Formerly the bundled `plan` skill; now built-in so it survives the Telegram/Discord command-menu caps.) | | `/init [notes]` | Generate or update `AGENTS.md` project instructions from a repo scan (port of Codex `/init`). The agent inspects manifests, layout, and toolchain configs with its read-only tools, then writes a concise `AGENTS.md` — or, if one exists, merge-updates it preserving your content. Optional notes steer the emphasis. Works in the CLI, the messaging gateway, and the TUI. | | `/cron` | Manage scheduled tasks (list, add/create, edit, pause, resume, run, remove) | | `/suggestions [accept\|dismiss N\|catalog\|clear]` (alias: `/suggest`) | Review suggested automations. Use `/suggestions` to list pending suggestions, `/suggestions accept <id>` to create the proposed automation, `/suggestions dismiss <id>` to reject one, `/suggestions catalog` to add curated starter automations, and `/suggestions clear` to clear resolved suggestion records. Accepted jobs preserve the current surface as the delivery origin. | | `/blueprint [name] [slot=value ...]` (alias: `/bp`) | Set up an automation from a blueprint template. Bare `/blueprint` lists the catalog; `/blueprint <name>` starts a guided slot-filling flow on the next agent turn; `/blueprint <name> slot=value ...` creates the job directly. | -| `/curator` | Background skill maintenance — `status`, `run`, `pin`, `archive`. See [Curator](/user-guide/features/curator). | -| `/kanban <action>` | Drive the multi-profile, multi-project collaboration board without leaving chat. Full `hermes kanban` surface is available: `/kanban list`, `/kanban show t_abc`, `/kanban create "title" --assignee X`, `/kanban comment t_abc "text"`, `/kanban unblock t_abc`, `/kanban dispatch`, etc. Multi-board support included: `/kanban boards list`, `/kanban boards create <slug>`, `/kanban boards switch <slug>`, `/kanban --board <slug> <action>`. See [Kanban slash command](/user-guide/features/kanban#kanban-slash-command). | +| `/curator` | Background skill maintenance — `status`, `run`, `pin`, `archive`. See [Curator](../user-guide/features/curator.md). | +| `/kanban <action>` | Drive the multi-profile, multi-project collaboration board without leaving chat. Full `hermes kanban` surface is available: `/kanban list`, `/kanban show t_abc`, `/kanban create "title" --assignee X`, `/kanban comment t_abc "text"`, `/kanban unblock t_abc`, `/kanban dispatch`, etc. Multi-board support included: `/kanban boards list`, `/kanban boards create <slug>`, `/kanban boards switch <slug>`, `/kanban --board <slug> <action>`. See [Kanban slash command](../user-guide/features/kanban.md#kanban-slash-command). | | `/reload-mcp` (alias: `/reload_mcp`) | Reload MCP servers from config.yaml and re-probe tool availability (credentials/daemons that appeared mid-session) | | `/reload-skills` (alias: `/reload_skills`) | Re-scan `~/.hermes/skills/` for newly installed or removed skills | | `/reload` | Reload `.env` variables into the running session (picks up new API keys without restarting) | | `/plugins` | List installed plugins and their status | -| `/pet [list\|<slug>]` | Toggle or adopt a [petdex](/user-guide/features/pets) mascot. `/pet` toggles the pane, `/pet list` shows installed pets, `/pet <slug>` adopts a specific one. | -| `/hatch <description>` (alias: `/generate-pet`) | Generate a brand-new petdex pet from a text description, using the configured image backend (OpenRouter / Nous Portal). See [Pets](/user-guide/features/pets). | +| `/pet [list\|<slug>]` | Toggle or adopt a [petdex](../user-guide/features/pets.md) mascot. `/pet` toggles the pane, `/pet list` shows installed pets, `/pet <slug>` adopts a specific one. | +| `/hatch <description>` (alias: `/generate-pet`) | Generate a brand-new petdex pet from a text description, using the configured image backend (OpenRouter / Nous Portal). See [Pets](../user-guide/features/pets.md). | ### Info @@ -235,7 +235,7 @@ Commands support prefix matching: typing `/h` resolves to `/help`, `/mod` resolv ## Messaging slash commands > **Slack thread commands (`!` prefix):** -> Slack itself blocks native slash commands inside message threads ("/queue is not supported in threads. Sorry!") and never delivers them to Hermes. Inside a Slack thread, use the `!` prefix instead — `!stop`, `!new`, `!status` — and the gateway dispatches it exactly like the slash form. `@Hermes !stop` and `@Hermes /stop` work in threads too. Only the first token is checked against the known command list, so messages like `!nice work` pass through to the agent unchanged. See [Using commands inside threads](/user-guide/messaging/slack#using-commands-inside-threads-the-cmd-prefix) for details. +> Slack itself blocks native slash commands inside message threads ("/queue is not supported in threads. Sorry!") and never delivers them to Hermes. Inside a Slack thread, use the `!` prefix instead — `!stop`, `!new`, `!status` — and the gateway dispatches it exactly like the slash form. `@Hermes !stop` and `@Hermes /stop` work in threads too. Only the first token is checked against the known command list, so messages like `!nice work` pass through to the agent unchanged. See [Using commands inside threads](../user-guide/messaging/slack.md#using-commands-inside-threads-the-cmd-prefix) for details. The messaging gateway supports the following built-in commands inside Telegram, Discord, Slack, WhatsApp, Signal, Email, Home Assistant, and Teams chats: @@ -253,7 +253,7 @@ The messaging gateway supports the following built-in commands inside Telegram, | `/undo` | Remove the last exchange. | | `/sethome` (alias: `/set-home`) | Mark the current chat as the platform home channel for deliveries. | | `/compress [here [N] \| focus topic]` | Manually compress conversation context. `/compress here [N]` keeps the most recent N exchanges (default 2) verbatim and summarizes the rest. A focus topic narrows what a full summary preserves. | -| `/topic [off\|help\|session-id]` | **Telegram DM only.** Manage user-managed multi-session topic mode. `/topic` enables it or shows status; `/topic off` disables it and clears bindings; `/topic help` shows usage; `/topic <session-id>` inside a topic restores a previous session. See [Multi-session DM mode](/user-guide/messaging/telegram#multi-session-dm-mode-topic). | +| `/topic [off\|help\|session-id]` | **Telegram DM only.** Manage user-managed multi-session topic mode. `/topic` enables it or shows status; `/topic off` disables it and clears bindings; `/topic help` shows usage; `/topic <session-id>` inside a topic restores a previous session. See [Multi-session DM mode](../user-guide/messaging/telegram.md#multi-session-dm-mode-topic). | | `/title [name]` | Set or show the session title. | | `/resume [name]` | Resume a previously named session. | | `/sessions [all] [search <query>]` | List previous sessions for this chat; the active session appears with a `(current)` marker. `/sessions search <query>` filters by title/id match (most recently active first); `/sessions all` lists across origins (admin only — non-admins get a notice and the chat-scoped list). | @@ -266,17 +266,17 @@ The messaging gateway supports the following built-in commands inside Telegram, | `/voice [on\|off\|tts\|join\|channel\|leave\|status]` | Control spoken replies in chat. `join`/`channel`/`leave` manage Discord voice-channel mode. | | `/rollback [number]` | List or restore filesystem checkpoints. | | `/diff [staged\|all\|session] [--stat]` | Show git changes in the working directory (fenced and truncated to platform message limits). `session` shows the cumulative diff of everything Hermes changed; `--stat` shows just the summary. | -| `/bg <prompt>` | Run a prompt in a separate background session. Results are delivered back to the same chat when the task finishes. See [Messaging Background Sessions](/user-guide/messaging/#background-sessions). | +| `/bg <prompt>` | Run a prompt in a separate background session. Results are delivered back to the same chat when the task finishes. See [Messaging Background Sessions](../user-guide/messaging/index.md#background-sessions). | | `/btw <question>` | Ask a side question about the current conversation without interrupting it. Answered from a transcript snapshot; the answer is sent to the chat when ready. | | `/queue <prompt>` (alias: `/q`) | Queue a prompt for the next turn without interrupting the current one. | | `/steer <prompt>` | Inject a message after the next tool call without interrupting — the model picks it up on its next iteration rather than as a new turn. | -| `/goal <text>` | Set a standing goal Hermes works toward across turns — our take on the Ralph loop. A judge model checks after each turn; if not done, Hermes auto-continues until it is, you pause/clear it, or the turn budget (default 20) is hit. Subcommands: `/goal status`, `/goal pause`, `/goal resume`, `/goal clear`. Safe to run mid-agent for status/pause/clear; setting a new goal requires `/stop` first. See [Persistent Goals](/user-guide/features/goals). | +| `/goal <text>` | Set a standing goal Hermes works toward across turns — our take on the Ralph loop. A judge model checks after each turn; if not done, Hermes auto-continues until it is, you pause/clear it, or the turn budget (default 20) is hit. Subcommands: `/goal status`, `/goal pause`, `/goal resume`, `/goal clear`. Safe to run mid-agent for status/pause/clear; setting a new goal requires `/stop` first. See [Persistent Goals](../user-guide/features/goals.md). | | `/subgoal <text>` | Append criteria to the active `/goal` mid-loop (`/subgoal`, `/subgoal remove <N>`, `/subgoal clear`). | | `/heartbeat every <interval> <prompt>` (alias: `/hb`) | Set a recurring prompt that re-enters this session when idle. Subcommands: `status`, `pause`, `resume`, `clear`. On Slack use `/hermes heartbeat …`. | -| `/loop [interval] <prompt> [--times N] [--until <condition>]` (alias: `/proactive`) | Re-run a prompt on a recurring interval in this session. Subcommands: `status`, `pause`, `resume`, `stop`. See [Loops](/user-guide/features/loops). | +| `/loop [interval] <prompt> [--times N] [--until <condition>]` (alias: `/proactive`) | Re-run a prompt on a recurring interval in this session. Subcommands: `status`, `pause`, `resume`, `stop`. See [Loops](../user-guide/features/loops.md). | | `/refine [focus]` | Run the memory/skill self-improvement review now, optionally with focus instructions. On Slack use `/hermes refine …`. | | `/review [instructions]` | Spawn an independent reviewer subagent for the work just discussed (PR, code, docs); its review re-enters this chat when done. On Slack use `/hermes review …`. | -| `/moa <prompt>` | Run one prompt through the default [Mixture of Agents](/user-guide/features/mixture-of-agents) preset, then restore the session model. | +| `/moa <prompt>` | Run one prompt through the default [Mixture of Agents](../user-guide/features/mixture-of-agents.md) preset, then restore the session model. | | `/branch [name]` (alias: `/fork`) | Branch the current session (explore a different path). | | `/agents` (alias: `/tasks`) | Show active agents and running tasks. | | `/sessions` | Browse and resume previous sessions. | @@ -291,9 +291,9 @@ The messaging gateway supports the following built-in commands inside Telegram, | `/curator [status\|run\|pin\|archive]` | Background skill maintenance controls. | | `/suggestions [accept\|dismiss N\|catalog\|clear]` | Review suggested automations right in chat. `/suggestions` lists pending suggestions, `catalog` adds curated starter automations, and `clear` prunes resolved suggestion records. Accepted suggestions keep this chat/thread as the job delivery origin. | | `/blueprint [name] [slot=value ...]` | Browse cron blueprints, start a guided slot-filling conversation, or create a blueprint job directly. Directly created jobs deliver back to the current chat/thread. | -| `/memory [pending\|approve\|reject\|approval]` | Review pending memory writes staged by the write-approval gate (`memory.write_approval`) — approve or reject them right in chat — and toggle the gate with `/memory approval on\|off`. See [Controlling memory writes](/user-guide/features/memory#controlling-memory-writes-write_approval). | +| `/memory [pending\|approve\|reject\|approval]` | Review pending memory writes staged by the write-approval gate (`memory.write_approval`) — approve or reject them right in chat — and toggle the gate with `/memory approval on\|off`. See [Controlling memory writes](../user-guide/features/memory.md#controlling-memory-writes-write_approval). | | `/skills [pending\|approve\|reject\|diff\|approval]` | Review pending **skill** writes staged by the write-approval gate (`skills.write_approval`). Shows a one-line gist per staged write; `/skills diff <id>` is truncated for chat — read the full diff on the CLI or in `~/.hermes/pending/skills/<id>.json`. Only appears when the gate is on (or staged writes remain); search/install stay CLI-only. | -| `/kanban <action>` | Drive the multi-profile, multi-project collaboration board from chat — identical argument surface to the CLI. Bypasses the running-agent guard, so `/kanban unblock t_abc`, `/kanban comment t_abc "…"`, `/kanban list --mine`, `/kanban boards switch <slug>`, etc. work mid-turn. `/kanban create …` auto-subscribes the originating chat to the new task's terminal events. See [Kanban slash command](/user-guide/features/kanban#kanban-slash-command). | +| `/kanban <action>` | Drive the multi-profile, multi-project collaboration board from chat — identical argument surface to the CLI. Bypasses the running-agent guard, so `/kanban unblock t_abc`, `/kanban comment t_abc "…"`, `/kanban list --mine`, `/kanban boards switch <slug>`, etc. work mid-turn. `/kanban create …` auto-subscribes the originating chat to the new task's terminal events. See [Kanban slash command](../user-guide/features/kanban.md#kanban-slash-command). | | `/platform <list\|pause\|resume> [name]` | Operate a running gateway platform right from chat. `/platform list` shows every adapter and its state (running, paused-by-breaker, manually-paused); `/platform pause <name>` stops dispatching new messages to that adapter without unloading it; `/platform resume <name>` re-enables it and clears a tripped circuit breaker once the upstream is healthy. | | `/reload-mcp` (alias: `/reload_mcp`) | Reload MCP servers from config and re-probe tool availability. | | `/verbose` | Cycle tool progress display. **Off by default on messaging** — enable with `display.tool_progress_command: true` in `config.yaml`. | diff --git a/website/docs/user-guide/configuration.md b/website/docs/user-guide/configuration.md index 006ecf1cb3..4c8e471466 100644 --- a/website/docs/user-guide/configuration.md +++ b/website/docs/user-guide/configuration.md @@ -9,7 +9,7 @@ description: "Configure Hermes Agent — config.yaml, providers, models, API key All settings are stored in the `~/.hermes/` directory for easy access. :::tip Easiest path to a working `config.yaml` -Run `hermes setup --portal` — one OAuth gets you a model provider and all four Tool Gateway tools without hand-editing YAML. Portal subscribers also get 10% off token-billed providers. See [Nous Portal](/integrations/nous-portal). +Run `hermes setup --portal` — one OAuth gets you a model provider and all four Tool Gateway tools without hand-editing YAML. Portal subscribers also get 10% off token-billed providers. See [Nous Portal](../integrations/nous-portal.md). ::: ## Directory Structure @@ -66,7 +66,7 @@ Secrets (API keys, bot tokens, passwords) go in `.env`. Everything else (model, :::tip Org deployments An administrator can pin specific config and secret values that a standard user cannot override, via a system-level managed directory. See -[Managed Scope](/user-guide/managed-scope). +[Managed Scope](./managed-scope.md). ::: ## Runtime Limits @@ -148,11 +148,11 @@ delegation: Multiple references in a single value work: `url: "${HOST}:${PORT}"`. If a referenced variable is not set, the placeholder is kept verbatim (`${UNDEFINED_VAR}` stays as-is) and a warning is logged. Bare `$VAR` is not expanded. -Under a [multiplexed multi-profile gateway](/user-guide/multi-profile-gateways), references in a profile's `config.yaml` resolve against **that profile's** `.env` (its secret scope), not the shared process environment — a `${MATRIX_ACCESS_TOKEN}` in profile B stays unresolved (kept verbatim, warning logged) unless B defines the variable itself. This holds wherever B's config is loaded inside the multiplexer: routed gateway turns, B's adapter startup, and B's cron jobs. Single-profile runs are unchanged. See [What is isolated per profile](/user-guide/multi-profile-gateways#what-is-isolated-per-profile) for the full list. +Under a [multiplexed multi-profile gateway](./multi-profile-gateways.md), references in a profile's `config.yaml` resolve against **that profile's** `.env` (its secret scope), not the shared process environment — a `${MATRIX_ACCESS_TOKEN}` in profile B stays unresolved (kept verbatim, warning logged) unless B defines the variable itself. This holds wherever B's config is loaded inside the multiplexer: routed gateway turns, B's adapter startup, and B's cron jobs. Single-profile runs are unchanged. See [What is isolated per profile](./multi-profile-gateways.md#what-is-isolated-per-profile) for the full list. Cursor-style SecretRef syntax is also accepted: `${env:VAR_NAME}` resolves exactly like `${VAR_NAME}` (the `env:` prefix is stripped), so MCP or provider snippets copied from Cursor / Claude configs work unchanged in both `config.yaml` and the `mcp_servers` block. Other SecretRef sources (`${file:...}`, `${vault:...}`, `${bitwarden:...}`) are **not** resolved inline — external secret backends inject their values into the environment at startup via the `secrets:` block, so reference them as `${env:NAME}` instead; unknown prefixes warn once and stay verbatim. -For AI provider setup (OpenRouter, Anthropic, Copilot, custom endpoints, self-hosted LLMs, fallback models, etc.), see [AI Providers](/integrations/providers). +For AI provider setup (OpenRouter, Anthropic, Copilot, custom endpoints, self-hosted LLMs, fallback models, etc.), see [AI Providers](../integrations/providers.md). ### Provider Timeouts @@ -775,7 +775,7 @@ skills: hermes config set skills.config.myplugin.path ~/myplugin-data ``` -For details on declaring config settings in your own skills, see [Creating Skills — Config Settings](/developer-guide/creating-skills#config-settings-configyaml). +For details on declaring config settings in your own skills, see [Creating Skills — Config Settings](../developer-guide/creating-skills.md#config-settings-configyaml). ### Auto-loading skills every session @@ -788,7 +788,7 @@ skills: - github-pr-workflow ``` -Resolved once per session when the system prompt is first built (so the prompt stays cache-stable; edits apply to the next session). Missing or disabled skills warn and are skipped; `--ignore-rules` / `HERMES_IGNORE_RULES=1` suppresses the list. Profile-scoped. See [CLI — persistent auto-load](/user-guide/cli#persistent-auto-load-via-config). +Resolved once per session when the system prompt is first built (so the prompt stays cache-stable; edits apply to the next session). Missing or disabled skills warn and are skipped; `--ignore-rules` / `HERMES_IGNORE_RULES=1` suppresses the list. Profile-scoped. See [CLI — persistent auto-load](./cli.md#persistent-auto-load-via-config). ### Guard on agent-created skill writes @@ -810,7 +810,7 @@ skills: write_approval: false # false = write freely (default) | true = stage every write for review ``` -When on, skill writes are staged under `~/.hermes/pending/skills/` and reviewed with `/skills pending`, `/skills diff <id>`, `/skills approve <id>`, `/skills reject <id>` — from the CLI or any messaging platform. Toggle at runtime with `/skills approval on|off`. Memory has the same gate (`memory.write_approval`, below). Full walkthrough: [Gating agent skill writes](/user-guide/features/skills#gating-agent-skill-writes-skillswrite_approval). +When on, skill writes are staged under `~/.hermes/pending/skills/` and reviewed with `/skills pending`, `/skills diff <id>`, `/skills approve <id>`, `/skills reject <id>` — from the CLI or any messaging platform. Toggle at runtime with `/skills approval on|off`. Memory has the same gate (`memory.write_approval`, below). Full walkthrough: [Gating agent skill writes](./features/skills.md#gating-agent-skill-writes-skillswrite_approval). ## Memory Configuration @@ -823,7 +823,7 @@ memory: write_approval: false # true = require approval before any memory write ``` -With `memory.write_approval: true`, memory writes need your approval before they land: interactive CLI turns prompt inline; messaging sessions and the background self-improvement review stage the write for `/memory pending` → `/memory approve <id>` / `/memory reject <id>` review. Toggle at runtime with `/memory approval on|off`. See [Controlling memory writes](/user-guide/features/memory#controlling-memory-writes-write_approval). +With `memory.write_approval: true`, memory writes need your approval before they land: interactive CLI turns prompt inline; messaging sessions and the background self-improvement review stage the write for `/memory pending` → `/memory approve <id>` / `/memory reject <id>` review. Toggle at runtime with `/memory approval on|off`. See [Controlling memory writes](./features/memory.md#controlling-memory-writes-write_approval). ## Context File Truncation @@ -1150,7 +1150,7 @@ Agent cache pressure: anon RSS 6802MB over budget 6656MB — evicting 5 LRU sess ## Context Engine -The context engine controls how conversations are managed when approaching the model's token limit. The built-in `compressor` engine uses lossy summarization (see [Context Compression](/developer-guide/context-compression-and-caching)). Plugin engines can replace it with alternative strategies. +The context engine controls how conversations are managed when approaching the model's token limit. The built-in `compressor` engine uses lossy summarization (see [Context Compression](../developer-guide/context-compression-and-caching.md)). Plugin engines can replace it with alternative strategies. ```yaml context: @@ -1166,7 +1166,7 @@ context: Plugin engines are **never auto-activated** — you must explicitly set `context.engine` to the plugin name. Available engines can be browsed and selected via `hermes plugins` → Provider Plugins → Context Engine. -See [Memory Providers](/user-guide/features/memory-providers) for the analogous single-select system for memory plugins. +See [Memory Providers](./features/memory-providers.md) for the analogous single-select system for memory plugins. ## Iteration Budget @@ -1187,7 +1187,7 @@ agent: `agent.budget_warning_ratio` is off by default for ordinary and delegated conversations. When set to a value strictly between `0` and `1` alongside a finite `max_turns`, Hermes appends one model-visible checkpoint notice to the latest tool result after the threshold is reached. The notice rearms each conversation turn and uses each agent's own iteration budget. It only appends to a current tool-result tail, never an older turn, and does not add a synthetic user/system message or change the existing exhaustion grace call. Dispatcher-owned Kanban workers receive a completion checkpoint at 90% by default (an explicit ratio changes that threshold), while their tools are still available. The checkpoint asks for verified completion or a durable progress comment, not premature success. -`agent.api_max_retries` controls how many times Hermes retries a provider API call on transient errors (rate limits, connection drops, 5xx) **before** fallback-provider switching engages. The default is `3` — four attempts total. If you have [fallback providers](/user-guide/features/fallback-providers) configured and want to fail over faster, drop this to `0` so the first transient error on your primary immediately hands off to the fallback instead of churning retries against the flaky endpoint. +`agent.api_max_retries` controls how many times Hermes retries a provider API call on transient errors (rate limits, connection drops, 5xx) **before** fallback-provider switching engages. The default is `3` — four attempts total. If you have [fallback providers](./features/fallback-providers.md) configured and want to fail over faster, drop this to `0` so the first transient error on your primary immediately hands off to the fallback instead of churning retries against the flaky endpoint. ## Wall-Clock Run Budget @@ -1227,7 +1227,7 @@ agent: The evidence that feeds this guard (which test/lint/build commands ran, which files were edited since) lives in `~/.hermes/verification_evidence.db`. That ledger is only written or created while the guard is enabled; with `verify_on_stop: false` nothing is recorded and an existing file can be deleted freely. -For a user/plugin policy gate at the same point — keep the agent going with your own checks — see the [`pre_verify` hook](/user-guide/features/hooks#pre_verify). +For a user/plugin policy gate at the same point — keep the agent going with your own checks — see the [`pre_verify` hook](./features/hooks.md#pre_verify). ## Standing Goals (`/goal`) @@ -1238,7 +1238,7 @@ goals: max_turns: 20 # Max continuation turns before Hermes auto-pauses the goal (default: 20) ``` -`max_turns` caps how many continuation turns a goal can drive before Hermes auto-pauses it and asks the user to `/goal resume`. It protects against judge false negatives (goal actually done but judge says continue) and unbounded model spend on fuzzy or unachievable goals. See [Goals](/user-guide/features/goals) for the full feature. +`max_turns` caps how many continuation turns a goal can drive before Hermes auto-pauses it and asks the user to `/goal resume`. It protects against judge false negatives (goal actually done but judge says continue) and unbounded model spend on fuzzy or unachievable goals. See [Goals](./features/goals.md) for the full feature. ### API Timeouts @@ -1309,7 +1309,7 @@ credential_pool_strategies: anthropic: least_used # always pick the least-used key ``` -Options: `fill_first` (default), `round_robin`, `least_used`, `random`. See [Credential Pools](/user-guide/features/credential-pools) for full documentation. +Options: `fill_first` (default), `round_robin`, `least_used`, `random`. See [Credential Pools](./features/credential-pools.md) for full documentation. ## Prompt caching @@ -1317,7 +1317,7 @@ Hermes turns on cross-session prompt caching automatically when the active provi For Claude on **native Anthropic**, **OpenRouter**, and **Nous Portal**, Hermes attaches `cache_control` breakpoints with the 1-hour TTL (`ttl: "1h"`) on the system prompt and skill blocks. The first send within a fresh hour pays full input rates; subsequent sends across any session within the same hour pull from the cache at the discounted cached-read rate. This means the system prompt, loaded skill content, and the early portion of any long-context include get reused across `hermes` sessions and across forked subagents for the first hour. -The Qwen Cloud (Alibaba DashScope) upstream caps cache TTL at 5 minutes, so Hermes uses the 5-minute breakpoint TTL there instead. Other Claude-via-third-party paths (AWS Bedrock, Azure Foundry) fall back to the provider's own caching defaults. xAI Grok uses a separate session-pinned conversation-id mechanism — see [xAI prompt caching](/integrations/providers#xai-grok--responses-api--prompt-caching). +The Qwen Cloud (Alibaba DashScope) upstream caps cache TTL at 5 minutes, so Hermes uses the 5-minute breakpoint TTL there instead. Other Claude-via-third-party paths (AWS Bedrock, Azure Foundry) fall back to the provider's own caching defaults. xAI Grok uses a separate session-pinned conversation-id mechanism — see [xAI prompt caching](../integrations/providers.md#xai-grok--responses-api--prompt-caching). No knob exists to disable this — caching is always-on and saves money even on single-turn conversations because the system prompt alone is a meaningful fraction of the input token count. @@ -1421,9 +1421,9 @@ This is the per-task counterpart of the global `agent.reasoning_effort`: run com If the endpoint rejects the reasoning field outright (a chat-only model behind an OpenAI-compatible relay answering `400 Unrecognized request argument supplied: reasoning_effort`, or the reversed wording `400 reasoning_effort 'none' unsupported; use minimal|low|medium|high|xhigh`), the auxiliary call is retried once with every reasoning field omitted, so the task (for example the session title) still completes with the endpoint's default behaviour. The main conversation applies the same recovery: when a route rejects the reasoning-off request Hermes sends for a thinking-only truncated continuation, the disable is dropped for the rest of the session and the request is retried with the route's default. -**Background review is different:** a same-model review fork always inherits the parent's reasoning effort. `auxiliary.background_review.reasoning_effort` is ignored on that path, including when the parent provider/model is explicitly selected. This preserves byte-identical reasoning settings, system prompt, full conversation snapshot, and tool definitions for prompt-cache parity; there is no independent-effort switch for same-model reviews. See [background review reasoning](/user-guide/features/memory#same-model-review-reasoning). When the review is routed to a different provider/model, `reasoning_effort` applies to that routed fork (unset = the routed provider's default). Hermes prints a one-time warning when the key is set but the review runs on the main model. +**Background review is different:** a same-model review fork always inherits the parent's reasoning effort. `auxiliary.background_review.reasoning_effort` is ignored on that path, including when the parent provider/model is explicitly selected. This preserves byte-identical reasoning settings, system prompt, full conversation snapshot, and tool definitions for prompt-cache parity; there is no independent-effort switch for same-model reviews. See [background review reasoning](./features/memory.md#same-model-review-reasoning). When the review is routed to a different provider/model, `reasoning_effort` applies to that routed fork (unset = the routed provider's default). Hermes prints a one-time warning when the key is set but the review runs on the main model. -**MoA also uses a different configuration:** reasoning depth for Mixture-of-Agents is configured **per slot** in the MoA preset (`moa.presets.<name>.reference_models[].reasoning_effort` / `aggregator.reasoning_effort`), not on the `moa_reference`/`moa_aggregator` auxiliary blocks — see [Mixture of Agents](/user-guide/features/mixture-of-agents). +**MoA also uses a different configuration:** reasoning depth for Mixture-of-Agents is configured **per slot** in the MoA preset (`moa.presets.<name>.reference_models[].reasoning_effort` / `aggregator.reasoning_effort`), not on the `moa_reference`/`moa_aggregator` auxiliary blocks — see [Mixture of Agents](./features/mixture-of-agents.md). ```yaml auxiliary: @@ -1435,7 +1435,7 @@ auxiliary: When `base_url` is set, Hermes ignores the provider and calls that endpoint directly (using `api_key` or `OPENAI_API_KEY` for auth). When only `provider` is set, Hermes uses that provider's built-in auth and base URL. -Available providers for auxiliary tasks: `auto`, `main`, plus any provider in the [provider registry](/reference/environment-variables) — `openrouter`, `nous`, `openai-codex`, `copilot`, `copilot-acp`, `anthropic`, `gemini`, `qwen-oauth`, `zai`, `kimi-coding`, `kimi-coding-cn`, `minimax`, `minimax-cn`, `minimax-oauth`, `deepseek`, `nvidia`, `xai`, `xai-oauth`, `ollama-cloud`, `alibaba`, `bedrock`, `huggingface`, `arcee`, `xiaomi`, `kilocode`, `opencode-zen`, `opencode-go`, `commandcode`, `commandcode-anthropic`, `ai-gateway`, `azure-foundry` — or any named custom provider from your `providers:` dict (e.g. `provider: "beans"`). +Available providers for auxiliary tasks: `auto`, `main`, plus any provider in the [provider registry](../reference/environment-variables.md) — `openrouter`, `nous`, `openai-codex`, `copilot`, `copilot-acp`, `anthropic`, `gemini`, `qwen-oauth`, `zai`, `kimi-coding`, `kimi-coding-cn`, `minimax`, `minimax-cn`, `minimax-oauth`, `deepseek`, `nvidia`, `xai`, `xai-oauth`, `ollama-cloud`, `alibaba`, `bedrock`, `huggingface`, `arcee`, `xiaomi`, `kilocode`, `opencode-zen`, `opencode-go`, `commandcode`, `commandcode-anthropic`, `ai-gateway`, `azure-foundry` — or any named custom provider from your `providers:` dict (e.g. `provider: "beans"`). Local OpenAI-compatible servers work under their own names too: `provider: ollama` (also `vllm`, `llamacpp`, `llama.cpp`) with a `base_url` such as `http://127.0.0.1:11434` and an empty `api_key` routes through the custom endpoint with a placeholder key, and a bare `host:port` base_url gets the `/v1` suffix automatically. @@ -1448,7 +1448,7 @@ Local OpenAI-compatible servers work under their own names too: `provider: ollam ::: :::warning `"main"` is for auxiliary tasks only -The `"main"` provider option means "use whatever provider my main agent uses" — it's only valid inside `auxiliary:`, `compression:`, and primary fallback entries (`fallback_providers:` or legacy `fallback_model:`). It is **not** a valid value for your top-level `model.provider` setting. If you use a custom OpenAI-compatible endpoint, set `provider: custom` in your `model:` section. See [AI Providers](/integrations/providers) for all main model provider options. +The `"main"` provider option means "use whatever provider my main agent uses" — it's only valid inside `auxiliary:`, `compression:`, and primary fallback entries (`fallback_providers:` or legacy `fallback_model:`). It is **not** a valid value for your top-level `model.provider` setting. If you use a custom OpenAI-compatible endpoint, set `provider: custom` in your `model:` section. See [AI Providers](../integrations/providers.md) for all main model provider options. ::: ### Full auxiliary config reference @@ -1553,7 +1553,7 @@ Each auxiliary task has a configurable `timeout` (in seconds). Defaults: vision ::: :::info -Context compression has its own `compression:` block for thresholds and an `auxiliary.compression:` block for model/provider settings — see [Context Compression](#context-compression) above. The primary fallback chain uses a top-level `fallback_providers:` list — see [Fallback Providers](/integrations/providers#fallback-providers). All three follow the same provider/model/base_url pattern. +Context compression has its own `compression:` block for thresholds and an `auxiliary.compression:` block for model/provider settings — see [Context Compression](#context-compression) above. The primary fallback chain uses a top-level `fallback_providers:` list — see [Fallback Providers](../integrations/providers.md#fallback-providers). All three follow the same provider/model/base_url pattern. ::: ### Per-task fallback chain for auxiliary tasks @@ -1586,7 +1586,7 @@ Each entry supports the same three knobs as any auxiliary task config: ### Native vision embed budgets (top-level `vision:`) -Separate from `auxiliary.vision` (which picks the describer model): when the *main* model is vision-capable, `vision_analyze` and browser screenshots embed real pixels into tool results that are re-sent every later turn. `vision.embed_target_bytes` (default `262144`, clamped 64 KiB..4 MiB) sizes one embed; `vision.max_calls_per_image` caps how often the same image may be embedded per session (unset = 3 inside delegated subagents, unlimited for the main agent; `0` = unlimited). See [Vision → Native embeds ride the session](/user-guide/features/vision#native-embeds-ride-the-session-visionembed_target_bytes-and-visionmax_calls_per_image). +Separate from `auxiliary.vision` (which picks the describer model): when the *main* model is vision-capable, `vision_analyze` and browser screenshots embed real pixels into tool results that are re-sent every later turn. `vision.embed_target_bytes` (default `262144`, clamped 64 KiB..4 MiB) sizes one embed; `vision.max_calls_per_image` caps how often the same image may be embedded per session (unset = 3 inside delegated subagents, unlimited for the main agent; `0` = unlimited). See [Vision → Native embeds ride the session](./features/vision.md#native-embeds-ride-the-session-visionembed_target_bytes-and-visionmax_calls_per_image). ### Limiting auxiliary concurrency @@ -1609,7 +1609,7 @@ The semaphore wraps the entire call including retries and fallbacks, so a single ### OpenRouter routing & Pareto Code for auxiliary tasks -When an auxiliary task resolves to OpenRouter (either explicitly or via `provider: "main"` while your main agent is on OpenRouter), the main agent's `provider_routing` and `openrouter.min_coding_score` settings **do not propagate** — by design, each auxiliary task is independent. To set OpenRouter provider preferences or use the [Pareto Code router](/integrations/providers#openrouter-pareto-code-router) for a specific aux task, set them per-task via `extra_body`: +When an auxiliary task resolves to OpenRouter (either explicitly or via `provider: "main"` while your main agent is on OpenRouter), the main agent's `provider_routing` and `openrouter.min_coding_score` settings **do not propagate** — by design, each auxiliary task is independent. To set OpenRouter provider preferences or use the [Pareto Code router](../integrations/providers.md#openrouter-pareto-code-router) for a specific aux task, set them per-task via `extra_body`: ```yaml auxiliary: @@ -1822,11 +1822,11 @@ The key matching is **spelling-tolerant** — any reasonable spelling will match - Exact matches take precedence over variants :::note -Model ids contain dots (`claude-opus-4.5`, `qwen3.6:27b`), which `hermes config set` treats as nesting separators. Escape them with a backslash to write the literal key — `hermes config set 'agent.reasoning_overrides.ollama-local/qwen3\.6:27b-q4_k_m' low` — or edit the YAML directly. See [Dots inside key names](/reference/cli-commands#dots-inside-key-names). +Model ids contain dots (`claude-opus-4.5`, `qwen3.6:27b`), which `hermes config set` treats as nesting separators. Escape them with a backslash to write the literal key — `hermes config set 'agent.reasoning_overrides.ollama-local/qwen3\.6:27b-q4_k_m' low` — or edit the YAML directly. See [Dots inside key names](../reference/cli-commands.md#dots-inside-key-names). ::: :::note Local OpenAI-compatible endpoints -A custom `base_url` (`http://localhost:11434/v1`, a vLLM, SGLang or router endpoint) receives the resolved effort — `agent.reasoning_effort` or the matching per-model override — as the standard top-level `reasoning_effort` request field, clamped to the values the OpenAI-compatible wire accepts (`none`, `minimal`, `low`, `medium`, `high`, `xhigh`, `max`). The nested `reasoning` object is reserved for endpoints known to accept it (Nous Portal, OpenRouter reasoning-capable models, GitHub Models) because arbitrary servers reject unknown fields with HTTP 400. If your server reads its thinking budget from a different field (Ollama's `think`, vLLM's `chat_template_kwargs`, a router-specific key), set it under the custom provider's [`extra_body`](/integrations/providers#named-custom-providers), which is merged into every request routed there. +A custom `base_url` (`http://localhost:11434/v1`, a vLLM, SGLang or router endpoint) receives the resolved effort — `agent.reasoning_effort` or the matching per-model override — as the standard top-level `reasoning_effort` request field, clamped to the values the OpenAI-compatible wire accepts (`none`, `minimal`, `low`, `medium`, `high`, `xhigh`, `max`). The nested `reasoning` object is reserved for endpoints known to accept it (Nous Portal, OpenRouter reasoning-capable models, GitHub Models) because arbitrary servers reject unknown fields with HTTP 400. If your server reads its thinking budget from a different field (Ollama's `think`, vLLM's `chat_template_kwargs`, a router-specific key), set it under the custom provider's [`extra_body`](../integrations/providers.md#named-custom-providers), which is merged into every request routed there. ::: **Resolution priority:** @@ -2340,7 +2340,7 @@ stt: prompt: "Hermes, Teknium, Nous Research, kanban, Ollama" ``` -**Composition.** The config value is the base. Plugins that register the [`pre_transcription`](/user-guide/features/hooks#pre_transcription) hook mutate on top of it, last-writer-wins per field. Multiple plugins' hints compose deterministically: plugin discovery loads plugins in sorted order by plugin id, and each plugin's callbacks run in its own registration order, so the same set of plugins always produces the same final prompt. A hook returning an empty string for `prompt` clears the config prompt for that request. Hooks may also override `language` and `model`; `file_path` is read-only and any attempt to change it is logged and dropped. With no hook registered and no `stt.prompt` set, the outgoing request is identical to previous releases. +**Composition.** The config value is the base. Plugins that register the [`pre_transcription`](./features/hooks.md#pre_transcription) hook mutate on top of it, last-writer-wins per field. Multiple plugins' hints compose deterministically: plugin discovery loads plugins in sorted order by plugin id, and each plugin's callbacks run in its own registration order, so the same set of plugins always produces the same final prompt. A hook returning an empty string for `prompt` clears the config prompt for that request. Hooks may also override `language` and `model`; `file_path` is read-only and any attempt to change it is logged and dropped. With no hook registered and no `stt.prompt` set, the outgoing request is identical to previous releases. **Provider support.** @@ -2376,7 +2376,7 @@ voice: silence_duration: 3.0 # Seconds of silence before auto-stop ``` -Use `/voice on` in the CLI to enable microphone mode, `record_key` to start/stop recording, and `/voice tts` to toggle spoken replies. See [Voice Mode](/user-guide/features/voice-mode) for end-to-end setup and platform-specific behavior. +Use `/voice on` in the CLI to enable microphone mode, `record_key` to start/stop recording, and `/voice tts` to toggle spoken replies. See [Voice Mode](./features/voice-mode.md) for end-to-end setup and platform-specific behavior. ## Streaming @@ -2458,7 +2458,7 @@ group_sessions_per_user: true # true = per-user isolation in groups/channels, f - Direct messages are unaffected. Hermes still keys DMs by chat/DM ID as usual. - Threads stay isolated from their parent channel either way; with `true`, each participant also gets their own session inside the thread. -For the behavior details and examples, see [Sessions](/user-guide/sessions) and the [Discord guide](/user-guide/messaging/discord). +For the behavior details and examples, see [Sessions](./sessions.md) and the [Discord guide](./messaging/discord.md). ## Unauthorized DM Behavior @@ -2586,9 +2586,9 @@ web: | **Perplexity** | `PERPLEXITY_API_KEY` | ✔ | ✔ (query-relevant snippets) | | **Exa** | `EXA_API_KEY` (optional — keyless free tier) | ✔ | ✔ | -**Backend selection:** The runtime always uses the stored `web.backend` selection (set via `hermes tools`; `nous` routes through the managed Tool Gateway). Only if no web backend has ever been selected is one auto-detected from available API keys: if only `SEARXNG_URL` is set, SearXNG is used; if only `EXA_API_KEY` is set, Exa; if only `TAVILY_API_KEY` is set, Tavily; if only `PERPLEXITY_API_KEY` is set, Perplexity; if only `PARALLEL_API_KEY` is set, Parallel; if only `KEENABLE_API_KEY` is set, Keenable. With **no selection and no credentials at all**, requests rotate round-robin across the keyless free-tier ring (Exa / Parallel / Firecrawl / Keenable) with automatic next-in-line failover on rate limits — see the [Web Search guide](/user-guide/features/web-search) for details. Once a selection exists, adding a key to `.env` does not change the route. Selecting Tavily, Firecrawl, or Keenable in `hermes tools` also works without a key. +**Backend selection:** The runtime always uses the stored `web.backend` selection (set via `hermes tools`; `nous` routes through the managed Tool Gateway). Only if no web backend has ever been selected is one auto-detected from available API keys: if only `SEARXNG_URL` is set, SearXNG is used; if only `EXA_API_KEY` is set, Exa; if only `TAVILY_API_KEY` is set, Tavily; if only `PERPLEXITY_API_KEY` is set, Perplexity; if only `PARALLEL_API_KEY` is set, Parallel; if only `KEENABLE_API_KEY` is set, Keenable. With **no selection and no credentials at all**, requests rotate round-robin across the keyless free-tier ring (Exa / Parallel / Firecrawl / Keenable) with automatic next-in-line failover on rate limits — see the [Web Search guide](./features/web-search.md) for details. Once a selection exists, adding a key to `.env` does not change the route. Selecting Tavily, Firecrawl, or Keenable in `hermes tools` also works without a key. -**SearXNG** is a free, self-hosted, privacy-respecting metasearch engine that queries 70+ search engines. No API key needed — just set `SEARXNG_URL` to your instance (e.g., `http://localhost:8080`). SearXNG is search-only; `web_extract` requires a separate extract provider (set `web.extract_backend`). See the [Web Search setup guide](/user-guide/features/web-search) for Docker setup instructions. +**SearXNG** is a free, self-hosted, privacy-respecting metasearch engine that queries 70+ search engines. No API key needed — just set `SEARXNG_URL` to your instance (e.g., `http://localhost:8080`). SearXNG is search-only; `web_extract` requires a separate extract provider (set `web.extract_backend`). See the [Web Search setup guide](./features/web-search.md) for Docker setup instructions. **Self-hosted Firecrawl:** Set `FIRECRAWL_API_URL` to point at your own instance. When a custom URL is set, the API key becomes optional (set `USE_DB_AUTHENTICATION=*** on the server to disable auth). @@ -2628,7 +2628,7 @@ browser: See the [browser feature page](./features/browser.md#browser_dialog) for the full dialog workflow. -The browser toolset supports multiple providers. See the [Browser feature page](/user-guide/features/browser) for details on Browserbase, Browser Use, and local Chromium-family CDP setup. +The browser toolset supports multiple providers. See the [Browser feature page](./features/browser.md) for details on Browserbase, Browser Use, and local Chromium-family CDP setup. ## Timezone @@ -2750,7 +2750,7 @@ approvals: - "*curl*|*sh*" ``` -Patterns are case-insensitive fnmatch globs and must be quoted in YAML (a bare leading `*` is a parse error). See [Security — User-Defined Deny Rules](/user-guide/security#user-defined-deny-rules-approvalsdeny) for details. +Patterns are case-insensitive fnmatch globs and must be quoted in YAML (a bare leading `*` is a parse error). See [Security — User-Defined Deny Rules](./security.md#user-defined-deny-rules-approvalsdeny) for details. ### Custom smart-approval policy @@ -2766,7 +2766,7 @@ approvals: ## Checkpoints -Automatic filesystem snapshots before destructive file operations. See the [Checkpoints & Rollback](/user-guide/checkpoints-and-rollback) for details. +Automatic filesystem snapshots before destructive file operations. See the [Checkpoints & Rollback](./checkpoints-and-rollback.md) for details. ```yaml checkpoints: @@ -2857,8 +2857,8 @@ Hermes uses two different context scopes: - All loaded context files are capped at `context_file_max_chars` characters (default 20,000) with smart truncation. See also: -- [Personality & SOUL.md](/user-guide/features/personality) -- [Context Files](/user-guide/features/context-files) +- [Personality & SOUL.md](./features/personality.md) +- [Context Files](./features/context-files.md) ## Working Directory @@ -2903,7 +2903,7 @@ onboarding: ## Dashboard -Configuration for the [web dashboard](/user-guide/features/web-dashboard) — visual theme, public URL, and authentication providers. The auth providers (OAuth, basic password, drain) are documented in detail on the web-dashboard page; this is the `config.yaml` shape. +Configuration for the [web dashboard](./features/web-dashboard.md) — visual theme, public URL, and authentication providers. The auth providers (OAuth, basic password, drain) are documented in detail on the web-dashboard page; this is the `config.yaml` shape. ```yaml dashboard: @@ -2935,7 +2935,7 @@ dashboard: - `show_token_analytics` — off by default. The Analytics page and token/cost figures are a **local lower-bound estimate** (they exclude auxiliary calls, retries, fallbacks, and cache writes), so they can read far below the provider bill. Set `true` only if you understand they're not billing. - `public_url` — when set, this is the complete authority (scheme + host + optional path prefix) the OAuth `redirect_uri` is built from. Set it for deploys behind reverse proxies that don't reliably forward `X-Forwarded-*` headers. Leave empty to use proxy-header reconstruction. - `trusted_proxies` — IP addresses or bounded CIDR networks allowed to supply `X-Forwarded-Proto` and `X-Forwarded-For`. Loopback remains trusted automatically. Configure this when the TLS reverse proxy connects from another container or host. Prefer the proxy's exact IP; use a small dedicated network only when its address is dynamic. Wildcards and `/0` networks are rejected. -- `oauth` / `basic_auth` / `drain_auth` — auth provider config read by the bundled dashboard-auth plugins. The drain secret itself is **not** set here; it's provisioned via the `HERMES_DASHBOARD_DRAIN_SECRET` env var. See [Web Dashboard](/user-guide/features/web-dashboard) for full auth setup. +- `oauth` / `basic_auth` / `drain_auth` — auth provider config read by the bundled dashboard-auth plugins. The drain secret itself is **not** set here; it's provisioned via the `HERMES_DASHBOARD_DRAIN_SECRET` env var. See [Web Dashboard](./features/web-dashboard.md) for full auth setup. - `ws_ping_interval` / `ws_ping_timeout` — WebSocket keepalive tuning for non-loopback binds (loopback connections never ping). Raise these on high-latency links (Tailscale, distant SSH tunnels) where the 20 s defaults can manufacture spurious 1006 disconnects. - `ssh_isolated_idle_grace_s` (default `900`) — a Desktop-owned `hermes serve --isolated` backend reached over SSH is detached from the SSH session on purpose, so a laptop that sleeps mid-connection cannot tear it down; each dark-wake reconnect used to leave another backend holding `state.db`. The backend now retires itself once no client WebSocket has been connected for this long and no agent turn is running (a turn keeps it alive; an unreadable turn state keeps it alive too). Set high if you rely on a detached backend finishing long work after the laptop sleeps. Such backends also send a slow WebSocket ping (60 s, 10 min timeout) so a half-open tunnel is noticed. - `ws_orphan_reap_grace_s` — how long a WS-detached session waits before the orphan reaper collects it. Raise alongside the keepalive values if clients reconnect slowly. Periodic session maintenance also completes cleanup for closed sockets and re-arms a missing orphan timer, so a detached chat cannot keep its ownership lease solely because its initial cleanup or timer was lost. Reconnecting cancels that timer; active delegated work and healthy running turns remain protected by the normal orphan-reaper checks. (`HERMES_TUI_WS_ORPHAN_REAP_GRACE_S` remains as an internal override.) diff --git a/website/docs/user-guide/features/cron.md b/website/docs/user-guide/features/cron.md index f9180d2d65..39634741d5 100644 --- a/website/docs/user-guide/features/cron.md +++ b/website/docs/user-guide/features/cron.md @@ -875,7 +875,7 @@ Semantics: #### Giving a script a credential -A script that must authenticate to an external service (an API token, a service-account key) gets it the same way terminal and `execute_code` children do — declare the variable name in the owning profile's `config.yaml` and define the value in that profile's `.env` (or an external [secret source](/user-guide/secrets/)): +A script that must authenticate to an external service (an API token, a service-account key) gets it the same way terminal and `execute_code` children do — declare the variable name in the owning profile's `config.yaml` and define the value in that profile's `.env` (or an external [secret source](../secrets/index.md)): ```yaml terminal: diff --git a/website/docs/user-guide/secrets/index.md b/website/docs/user-guide/secrets/index.md index f2fcb474c7..102b5450ee 100644 --- a/website/docs/user-guide/secrets/index.md +++ b/website/docs/user-guide/secrets/index.md @@ -45,7 +45,7 @@ Both apply to every source — bundled and plugin — because they live in the o ## Secrets in child processes -Terminal commands, `execute_code` sandboxes and [`no_agent` cron scripts](/user-guide/features/cron#giving-a-script-a-credential) run with a sanitized environment: Hermes-managed credentials are stripped, and only variables you declare in `terminal.env_passthrough` (or a loaded skill's `required_environment_variables`) are forwarded. A declared variable is forwarded with the **owning profile's** value — from that profile's `.env` or its secret sources — even when the profile is served by a multi-profile gateway or the Desktop/dashboard backend and its secrets never entered the process environment. A profile's declared value never reaches another profile's children, and the launch profile's `.env` credentials are dropped from children that run for a served profile. Provider credentials cannot be declared; see [Security → Credential scoping](/user-guide/security). +Terminal commands, `execute_code` sandboxes and [`no_agent` cron scripts](../features/cron.md#giving-a-script-a-credential) run with a sanitized environment: Hermes-managed credentials are stripped, and only variables you declare in `terminal.env_passthrough` (or a loaded skill's `required_environment_variables`) are forwarded. A declared variable is forwarded with the **owning profile's** value — from that profile's `.env` or its secret sources — even when the profile is served by a multi-profile gateway or the Desktop/dashboard backend and its secrets never entered the process environment. A profile's declared value never reaches another profile's children, and the launch profile's `.env` credentials are dropped from children that run for a served profile. Provider credentials cannot be declared; see [Security → Credential scoping](../security.md). ## Adding your own backend diff --git a/website/i18n/zh-Hans/docusaurus-plugin-content-docs/current/guides/run-hermes-with-nous-portal.md b/website/i18n/zh-Hans/docusaurus-plugin-content-docs/current/guides/run-hermes-with-nous-portal.md index c9b9c1b3b0..2c312207f3 100644 --- a/website/i18n/zh-Hans/docusaurus-plugin-content-docs/current/guides/run-hermes-with-nous-portal.md +++ b/website/i18n/zh-Hans/docusaurus-plugin-content-docs/current/guides/run-hermes-with-nous-portal.md @@ -6,12 +6,12 @@ description: "完整操作指南：订阅、配置、切换模型、启用 gatew # 通过 Nous Portal 运行 Hermes Agent -本指南带你从头到尾完成在 [Nous Portal](https://portal.nousresearch.com) 订阅下运行 Hermes Agent 的全过程——从注册账号到验证每个工具的路由是否正确。如果你只想了解 Portal 的概述及订阅内容，请参阅 [Nous Portal 集成页面](/integrations/nous-portal)。本页是操作步骤脚本。 +本指南带你从头到尾完成在 [Nous Portal](https://portal.nousresearch.com) 订阅下运行 Hermes Agent 的全过程——从注册账号到验证每个工具的路由是否正确。如果你只想了解 Portal 的概述及订阅内容，请参阅 [Nous Portal 集成页面](../integrations/nous-portal.md)。本页是操作步骤脚本。 ## 前提条件 -- 已安装 Hermes Agent（[快速入门](/getting-started/quickstart)） -- 在你正在配置的机器上有可用的浏览器（或 SSH 端口转发——参见 [OAuth over SSH](/guides/oauth-over-ssh)） +- 已安装 Hermes Agent（[快速入门](../getting-started/quickstart.md)） +- 在你正在配置的机器上有可用的浏览器（或 SSH 端口转发——参见 [OAuth over SSH](./oauth-over-ssh.md)） - 约 5 分钟时间 你**不需要**：OpenAI 密钥、Anthropic 密钥、Firecrawl 账号、FAL 账号、Browser Use 账号，或任何其他按供应商分配的凭证。这正是 Portal 的意义所在。 @@ -52,7 +52,7 @@ hermes auth add nous --type oauth # 然后重新运行 `hermes setup --portal` 以连接 provider + gateway ``` -完整操作说明（包括 ProxyJump 链、mosh/tmux 和 ControlMaster 注意事项）请参阅 [OAuth over SSH / 远程主机](/guides/oauth-over-ssh)。 +完整操作说明（包括 ProxyJump 链、mosh/tmux 和 ControlMaster 注意事项）请参阅 [OAuth over SSH / 远程主机](./oauth-over-ssh.md)。 ## 3. 验证配置是否成功 @@ -120,7 +120,7 @@ hermes config set model.default anthropic/claude-sonnet-4.6 ### 不要在 agent 任务中使用 Hermes-4 -Hermes-4-70B 和 Hermes-4-405B 在 Portal 上以大幅折扣提供，但它们是**对话/推理模型**，并非针对工具调用优化的模型。它们在多步骤 agent 循环中表现不佳。请通过[订阅代理](/user-guide/features/subscription-proxy)从非 agent 工具中将它们用于对话或研究工作。对于 Hermes Agent 本身，请坚持使用上述前沿 agentic 模型。 +Hermes-4-70B 和 Hermes-4-405B 在 Portal 上以大幅折扣提供，但它们是**对话/推理模型**，并非针对工具调用优化的模型。它们在多步骤 agent 循环中表现不佳。请通过[订阅代理](../user-guide/features/subscription-proxy.md)从非 agent 工具中将它们用于对话或研究工作。对于 Hermes Agent 本身，请坚持使用上述前沿 agentic 模型。 Portal 的[信息页面](https://portal.nousresearch.com/info)也有此说明——这是 Nous 官方指导，并非仅代表 Hermes 一方的意见。 @@ -146,7 +146,7 @@ hermes portal tools ## 7. （可选）启用语音模式 -由于 Tool Gateway 包含 OpenAI TTS，无需单独的 OpenAI 密钥即可使用[语音模式](/user-guide/features/voice-mode)： +由于 Tool Gateway 包含 OpenAI TTS，无需单独的 OpenAI 密钥即可使用[语音模式](../user-guide/features/voice-mode.md)： ```bash hermes setup voice @@ -158,7 +158,7 @@ hermes setup voice ## 8. （可选）Cron 定时任务与常驻工作流 -Portal 订阅对 [cron 定时任务](/user-guide/features/cron)和[批处理](/user-guide/features/batch-processing)的支持方式与交互式对话相同——OAuth refresh token 会自动复用。无需额外配置，直接安排 cron 任务，费用将计入你的订阅。 +Portal 订阅对 [cron 定时任务](../user-guide/features/cron.md)和[批处理](../user-guide/features/batch-processing.md)的支持方式与交互式对话相同——OAuth refresh token 会自动复用。无需额外配置，直接安排 cron 任务，费用将计入你的订阅。 ```bash hermes cron add "Daily AI news summary" "every day at 9am" \ @@ -169,7 +169,7 @@ hermes cron add "Daily AI news summary" "every day at 9am" \ ## Profiles 与多用户配置 -如果你使用 [Hermes profiles](/user-guide/profiles)（例如每个项目单独一套配置），每个 profile 都是独立的凭证孤岛：从未登录过 Portal 的 profile 会直接失败，而不会采用其他 profile 的会话。请在每个 profile 上用 `hermes -p <name> portal` 登录一次——如果机器上已有共享的 Portal 会话，它会提示导入且无需再走浏览器流程；此后共享 token 存储会让该 profile 的令牌保持最新。参见 [Profile 配置](/integrations/nous-portal#profile-setup)。 +如果你使用 [Hermes profiles](../user-guide/profiles.md)（例如每个项目单独一套配置），每个 profile 都是独立的凭证孤岛：从未登录过 Portal 的 profile 会直接失败，而不会采用其他 profile 的会话。请在每个 profile 上用 `hermes -p <name> portal` 登录一次——如果机器上已有共享的 Portal 会话，它会提示导入且无需再走浏览器流程；此后共享 token 存储会让该 profile 的令牌保持最新。参见 [Profile 配置](../integrations/nous-portal.md#profile-setup)。 对于多人共用一台机器的团队场景，每个人有自己的 Portal 账号 → 每个 home 目录保存各自的 `~/.hermes/auth.json` → 用户之间不共享 token。这是正确的边界划分。 @@ -183,7 +183,7 @@ OAuth 流程未完成。重新运行： hermes portal ``` -如果浏览器未打开或回调失败，你可能在远程/无头主机上——参见 [OAuth over SSH](/guides/oauth-over-ssh) 了解端口转发的解决方案。 +如果浏览器未打开或回调失败，你可能在远程/无头主机上——参见 [OAuth over SSH](./oauth-over-ssh.md) 了解端口转发的解决方案。 ### "Model: currently openrouter"（或其他 provider）而非"using Nous as inference provider" @@ -265,9 +265,9 @@ hermes auth logout nous # 清除本地 refresh token ## 另请参阅 -- **[Nous Portal 集成页面](/integrations/nous-portal)** — 订阅内容概述 -- **[Tool Gateway](/user-guide/features/tool-gateway)** — 每个 gateway 路由工具的完整说明 -- **[订阅代理](/user-guide/features/subscription-proxy)** — 在非 Hermes 工具中使用你的 Portal 订阅 -- **[语音模式](/user-guide/features/voice-mode)** — 在 Portal 订阅上配置语音对话 -- **[OAuth over SSH](/guides/oauth-over-ssh)** — 远程/无头主机登录方案 -- **[Profiles](/user-guide/profiles)** — 在多个 Hermes 配置之间共享一个 Portal 登录 +- **[Nous Portal 集成页面](../integrations/nous-portal.md)** — 订阅内容概述 +- **[Tool Gateway](../user-guide/features/tool-gateway.md)** — 每个 gateway 路由工具的完整说明 +- **[订阅代理](../user-guide/features/subscription-proxy.md)** — 在非 Hermes 工具中使用你的 Portal 订阅 +- **[语音模式](../user-guide/features/voice-mode.md)** — 在 Portal 订阅上配置语音对话 +- **[OAuth over SSH](./oauth-over-ssh.md)** — 远程/无头主机登录方案 +- **[Profiles](../user-guide/profiles.md)** — 在多个 Hermes 配置之间共享一个 Portal 登录 diff --git a/website/i18n/zh-Hans/docusaurus-plugin-content-docs/current/integrations/nous-portal.md b/website/i18n/zh-Hans/docusaurus-plugin-content-docs/current/integrations/nous-portal.md index ac0776acda..c7f74eac67 100644 --- a/website/i18n/zh-Hans/docusaurus-plugin-content-docs/current/integrations/nous-portal.md +++ b/website/i18n/zh-Hans/docusaurus-plugin-content-docs/current/integrations/nous-portal.md @@ -46,13 +46,13 @@ Portal 代理了来自整个生态系统的精选 agentic 模型目录——统 ### Nous Tool Gateway -同一订阅还解锁了 [Tool Gateway](/user-guide/features/tool-gateway)，将 Hermes Agent 的工具调用路由至 Nous 托管的基础设施。五个后端，一次登录： +同一订阅还解锁了 [Tool Gateway](../user-guide/features/tool-gateway.md)，将 Hermes Agent 的工具调用路由至 Nous 托管的基础设施。五个后端，一次登录： | 工具 | 合作方 | 功能说明 | |------|---------|--------------| | **网页搜索与抓取** | Firecrawl | Agent 级搜索与整页内容提取。无需 Firecrawl API 密钥，无需管理速率限制。 | | **图像生成** | FAL | 单一端点下的九个模型：FLUX 2 Klein 9B、FLUX 2 Pro、Z-Image Turbo、Nano Banana Pro（Gemini 3 Pro Image）、GPT Image 1.5、GPT Image 2、Ideogram V3、Recraft V4 Pro、Qwen Image。 | -| **文字转语音** | OpenAI TTS | 无需独立 OpenAI 密钥的高质量 TTS。在各消息平台上启用[语音模式](/user-guide/features/voice-mode)。 | +| **文字转语音** | OpenAI TTS | 无需独立 OpenAI 密钥的高质量 TTS。在各消息平台上启用[语音模式](../user-guide/features/voice-mode.md)。 | | **云端浏览器自动化** | Browser Use | 用于 `browser_navigate`、`browser_click`、`browser_type`、`browser_vision` 的无头 Chromium 会话。无需 Browserbase 账号。 | | **云端终端沙箱** | Modal | 用于代码执行的无服务器终端沙箱（可选附加项）。 | @@ -66,13 +66,13 @@ Portal 代理了来自整个生态系统的精选 agentic 模型目录——统 ### 跨平台一致性 -[原生 Windows](/user-guide/windows-native) 上，逐个配置 API 密钥是其最大痛点——在 Windows 上分别安装 Firecrawl 账号、FAL 账号、Browser Use 账号、OpenAI 密钥，是整个 agent 配置过程中摩擦最高的部分。Portal 订阅消除了这一问题：一次 OAuth 覆盖模型和所有 gateway 工具，Windows 用户无需手动配置四个后端，即可获得与 macOS/Linux 相同的体验。 +[原生 Windows](../user-guide/windows-native.md) 上，逐个配置 API 密钥是其最大痛点——在 Windows 上分别安装 Firecrawl 账号、FAL 账号、Browser Use 账号、OpenAI 密钥，是整个 agent 配置过程中摩擦最高的部分。Portal 订阅消除了这一问题：一次 OAuth 覆盖模型和所有 gateway 工具，Windows 用户无需手动配置四个后端，即可获得与 macOS/Linux 相同的体验。 ## 关于 Hermes 4 的说明 Nous Research 自家的 **Hermes 4** 系列（Hermes-4-70B、Hermes-4-405B）通过 Portal 提供，享有大幅折扣。这些是**前沿混合推理对话模型**——在数学、科学、指令遵循、schema 遵从、角色扮演和长文写作方面表现出色。 -但**不建议在 Hermes Agent 内部使用它们**。Hermes 4 针对对话和推理进行了调优，而非 agent 所依赖的高频工具调用循环。请将它们用于研究工作流，或通过[订阅代理](/user-guide/features/subscription-proxy)从其他工具调用——但在 agent 场景下，请从目录中选择前沿 agentic 模型： +但**不建议在 Hermes Agent 内部使用它们**。Hermes 4 针对对话和推理进行了调优，而非 agent 所依赖的高频工具调用循环。请将它们用于研究工作流，或通过[订阅代理](../user-guide/features/subscription-proxy.md)从其他工具调用——但在 agent 场景下，请从目录中选择前沿 agentic 模型： ```bash /model anthropic/claude-sonnet-4.6 # 最佳通用 agentic 模型 @@ -116,11 +116,11 @@ hermes model ### 无头环境 / SSH / 远程配置 -OAuth 需要浏览器，但回调的 loopback 运行在 Hermes 所在的机器上。对于远程主机，请参阅 [OAuth over SSH / 远程主机](/guides/oauth-over-ssh)——与其他基于 OAuth 的提供商相同的方式同样适用于 Portal（`ssh -L` 端口转发）。 +OAuth 需要浏览器，但回调的 loopback 运行在 Hermes 所在的机器上。对于远程主机，请参阅 [OAuth over SSH / 远程主机](../guides/oauth-over-ssh.md)——与其他基于 OAuth 的提供商相同的方式同样适用于 Portal（`ssh -L` 端口转发）。 ### Profile 配置 {#profile-setup} -如果你使用 [Hermes profiles（配置文件）](/user-guide/profiles)，Portal 的 refresh token 会通过共享令牌存储在各 profile 间共享——但该存储**只刷新已有的登录，不会创建新登录**。各 profile 是相互独立的孤岛（[#111724](https://github.com/NousResearch/hermes-agent/issues/111724)），因此从未登录过 Portal 的 profile 没有自己的 Nous 凭证：启动时它会直接失败，提示 `Profile '<name>' is not connected to any AI provider yet`，而不会静默采用其他 profile 的会话。 +如果你使用 [Hermes profiles（配置文件）](../user-guide/profiles.md)，Portal 的 refresh token 会通过共享令牌存储在各 profile 间共享——但该存储**只刷新已有的登录，不会创建新登录**。各 profile 是相互独立的孤岛（[#111724](https://github.com/NousResearch/hermes-agent/issues/111724)），因此从未登录过 Portal 的 profile 没有自己的 Nous 凭证：启动时它会直接失败，提示 `Profile '<name>' is not connected to any AI provider yet`，而不会静默采用其他 profile 的会话。 **每个 profile 都需登录一次**，命令为 `hermes -p <name> portal`（即 `hermes -p <name> auth add nous --type oauth` 的别名）。如果机器上已有共享的 Portal 会话，该命令会提示导入——确认一次即可，无需再走浏览器流程。首次导入后该 profile 保留自己的状态，只要任一 profile 刷新或重新登录，共享存储便会让它的令牌保持最新。从已登录的 profile 执行 `hermes profile create <name> --clone-all` 也会一并带上 Portal 登录（克隆时只会剥离 Anthropic/Codex 这类一次性授权）。 @@ -190,7 +190,7 @@ hermes tools # → TTS → "Nous Subscription" ``` -Tool Gateway 是按工具单独选择启用的，而非全部或全不。完整的每工具配置矩阵请参阅 [Tool Gateway 文档](/user-guide/features/tool-gateway)。 +Tool Gateway 是按工具单独选择启用的，而非全部或全不。完整的每工具配置矩阵请参阅 [Tool Gateway 文档](../user-guide/features/tool-gateway.md)。 ### 订阅管理 @@ -266,9 +266,9 @@ Portal 会为每个模型选择合适的后端——部分模型通过 OpenRoute ## 另请参阅 -- **[Tool Gateway](/user-guide/features/tool-gateway)** —— 每个 gateway 工具的完整详情、每工具配置及定价 -- **[订阅代理](/user-guide/features/subscription-proxy)** —— 在非 Hermes 工具（其他 agent、脚本、第三方客户端）中使用你的 Portal 订阅 -- **[语音模式](/user-guide/features/voice-mode)** —— 使用 Portal 的 OpenAI TTS 进行语音对话 -- **[AI 提供商](/integrations/providers)** —— 完整提供商目录，供对比参考 -- **[OAuth over SSH](/guides/oauth-over-ssh)** —— 从远程主机或纯浏览器环境登录 -- **[Profiles](/user-guide/profiles)** —— 多个 Hermes 配置共享一个 Portal 登录 +- **[Tool Gateway](../user-guide/features/tool-gateway.md)** —— 每个 gateway 工具的完整详情、每工具配置及定价 +- **[订阅代理](../user-guide/features/subscription-proxy.md)** —— 在非 Hermes 工具（其他 agent、脚本、第三方客户端）中使用你的 Portal 订阅 +- **[语音模式](../user-guide/features/voice-mode.md)** —— 使用 Portal 的 OpenAI TTS 进行语音对话 +- **[AI 提供商](./providers.md)** —— 完整提供商目录，供对比参考 +- **[OAuth over SSH](../guides/oauth-over-ssh.md)** —— 从远程主机或纯浏览器环境登录 +- **[Profiles](../user-guide/profiles.md)** —— 多个 Hermes 配置共享一个 Portal 登录