docs: eight small accuracy fixes from open type/docs issues
Each fix verified against main @ ee84ccd on 2026-09-08.
- windows-native: the troubleshooting entry told users to set HERMES_GATEWAY_FORCE_STARTUP (no code reads it), query a task named HermesGateway (hermes_cli/gateway_windows.py names it Hermes_Gateway), and described the Startup-folder fallback as a cmd.exe shortcut (it writes a .vbs run via wscript.exe). Closes #88077.
- faq: 'hermes config set HERMES_MODEL ...' does not change the default model; 'model.default' does. Closes #65855.
- messaging/index, slash-commands, irc: gateway settings are read from ~/.hermes/config.yaml (gateway/config.py), not gateway-config.yaml. Closes #65857, closes #78276.
- telegram: reaction lifecycle is 👀 then 👍/👎 (plugins/platforms/telegram/adapter.py on_processing_complete), docs said ✅/❌. Closes #78698.
- plugins: bundled memory providers win on a name collision (plugins/memory/__init__.py docstring: bundled, user, project, entry point, first seen wins); the page said user plugins override. Model providers keep the documented last-writer-wins. Closes #100281.
- architecture, index: terminal backend count is seven (tools/terminal_tool.py: local, docker, singularity, modal, daytona, vercel_sandbox, ssh); two surfaces said six. Closes #78252.
- quickstart: the Portal quick path was called 'free'; the login is free, the inference is billed to the subscription. Wording now matches integrations/nous-portal. Closes #78254.
This commit is contained in:
witcheer
@@ -40,7 +40,7 @@ This page is the top-level map of Hermes Agent internals. Use it to orient yours
|
||||
▼ ▼
|
||||
┌───────────────────┐ ┌──────────────────────┐
|
||||
│ Session Storage │ │ Tool Backends │
|
||||
│ (SQLite + FTS5) │ │ Terminal (6 backends) │
|
||||
│ (SQLite + FTS5) │ │ Terminal (7 backends) │
|
||||
│ hermes_state.py │ │ Browser (5 backends) │
|
||||
│ gateway/session.py│ │ Web (4 backends) │
|
||||
└───────────────────┘ │ MCP (dynamic) │
|
||||
|
||||
@@ -98,7 +98,7 @@ That logs you in, sets Nous as your provider, and turns on the Tool Gateway in o
|
||||
:::info Setup modes
|
||||
On a fresh install, `hermes setup` offers three modes:
|
||||
|
||||
- **Quick Setup (Nous Portal)** — free OAuth login, no API keys; sets up a model plus the Tool Gateway tools. The recommended fast path.
|
||||
- **Quick Setup (Nous Portal)** — OAuth login, no API keys to manage; sets up a model plus the Tool Gateway tools, billed to your [Nous Portal subscription](/integrations/nous-portal). The recommended fast path.
|
||||
- **Full Setup** — walk through every provider, tool, and option yourself (bring your own keys).
|
||||
- **Blank Slate** — everything starts **off** except the bare minimum needed to run an agent: **provider & model, the File Operations toolset, and the Terminal toolset**. No web, browser, code execution, vision, memory, delegation, cron, skills, plugins, or MCP servers — and compression, checkpoints, smart routing, and memory capture are all disabled. After the minimal baseline is applied, you choose one of two paths: **start with everything disabled** (finish now with the minimal agent), or **walk through all configurations** (opt in to tools, skills, plugins, MCP, and messaging). Pick this when you want a minimal, fully-controlled agent and intend to enable only exactly what you need.
|
||||
|
||||
|
||||
@@ -134,7 +134,7 @@ It's not a coding copilot tethered to an IDE or a chatbot wrapper around a singl
|
||||
## Key Features
|
||||
|
||||
- **A closed learning loop** — Agent-curated memory with periodic nudges, autonomous skill creation, skill self-improvement during use, FTS5 cross-session recall with LLM summarization, and [Honcho](https://github.com/plastic-labs/honcho) dialectic user modeling
|
||||
- **Runs anywhere, not just your laptop** — 6 terminal backends: local, Docker, SSH, Daytona, Singularity, Modal. Daytona and Modal offer serverless persistence — your environment hibernates when idle, costing nearly nothing
|
||||
- **Runs anywhere, not just your laptop** — 7 terminal backends: local, Docker, SSH, Daytona, Singularity, Modal, Vercel Sandbox. Daytona and Modal offer serverless persistence — your environment hibernates when idle, costing nearly nothing
|
||||
- **Lives where you do** — CLI, Telegram, Discord, Slack, WhatsApp, Signal, Matrix, Mattermost, Email, SMS, DingTalk, Feishu, WeCom, Weixin, QQ Bot, Yuanbao, BlueBubbles, Home Assistant, Microsoft Teams, Google Chat, and more — 20+ platforms from one gateway
|
||||
- **Built by model trainers** — Created by [Nous Research](https://nousresearch.com), the lab behind Hermes, Nomos, and Psyche. Works with [Nous Portal](https://portal.nousresearch.com), [OpenRouter](https://openrouter.ai), OpenAI, or any endpoint
|
||||
- **Scheduled automations** — Built-in cron with delivery to any platform
|
||||
|
||||
@@ -284,7 +284,7 @@ Make sure the key matches the provider. An OpenAI key won't work with OpenRouter
|
||||
hermes model
|
||||
|
||||
# Set a valid model
|
||||
hermes config set HERMES_MODEL anthropic/claude-opus-4.7
|
||||
hermes config set model.default anthropic/claude-opus-4.7
|
||||
|
||||
# Or specify per-session
|
||||
hermes chat --model openrouter/meta-llama/llama-3.1-70b-instruct
|
||||
|
||||
@@ -15,7 +15,7 @@ Installed skills are also exposed as dynamic slash commands on both surfaces. (`
|
||||
|
||||
## Permissions and admin/user split
|
||||
|
||||
Every messaging platform that supports a per-user allowlist (Telegram, Discord, Slack, Matrix, Mattermost, Signal, …) also supports a two-tier slash command split: **admins** get every registered command, **regular users** only get the names you list in `user_allowed_commands` (plus the always-allowed floor `/help` and `/whoami`). Configure `allow_admin_from` and `user_allowed_commands` (and the per-group equivalents `group_allow_admin_from` / `group_user_allowed_commands`) inside the platform's `extra:` block in `~/.hermes/gateway-config.yaml`.
|
||||
Every messaging platform that supports a per-user allowlist (Telegram, Discord, Slack, Matrix, Mattermost, Signal, …) also supports a two-tier slash command split: **admins** get every registered command, **regular users** only get the names you list in `user_allowed_commands` (plus the always-allowed floor `/help` and `/whoami`). Configure `allow_admin_from` and `user_allowed_commands` (and the per-group equivalents `group_allow_admin_from` / `group_user_allowed_commands`) inside the platform's `extra:` block in `~/.hermes/config.yaml`.
|
||||
|
||||
See the per-platform docs for examples — the structure is identical across platforms:
|
||||
|
||||
|
||||
@@ -144,7 +144,7 @@ Within each source, Hermes also recognizes sub-category directories that route p
|
||||
| `plugins/context_engine/<name>/` | Context-compression engines (`ctx.register_context_engine()`) | **Own loader** in `plugins/context_engine/__init__.py` (one active at a time) |
|
||||
| `plugins/model-providers/<name>/` | LLM provider profiles (`register_provider(ProviderProfile(...))`) | **Own loader** in `providers/__init__.py` (lazily scanned on first `get_provider_profile()` call) |
|
||||
|
||||
User plugins at `~/.hermes/plugins/model-providers/<name>/` and `~/.hermes/plugins/memory/<name>/` override bundled plugins of the same name — last-writer-wins in `register_provider()` / `register_memory_provider()`. Drop a directory in, and it replaces the built-in without any repo edits.
|
||||
User plugins at `~/.hermes/plugins/model-providers/<name>/` override bundled model providers of the same name (last-writer-wins in `register_provider()`), so you can replace a built-in provider profile without any repo edits. Memory providers resolve the other way round: for `~/.hermes/plugins/memory/<name>/` the **bundled** provider wins on a name collision (bundled, then user, then project, then entry points; first seen wins), so a user memory provider needs its own unique name.
|
||||
|
||||
## Plugins are opt-in (with a few exceptions)
|
||||
|
||||
|
||||
@@ -284,7 +284,7 @@ continuation, not the history loaded when you send a message.
|
||||
|
||||
## Per-Channel Model & System Prompt Overrides
|
||||
|
||||
Different channels can run different models and personas from a **single gateway** — e.g. a cheap fast model in `#daily` and a frontier model with a specialist prompt in `#dev`. Configure `channel_overrides` under the platform in `~/.hermes/gateway-config.yaml`:
|
||||
Different channels can run different models and personas from a **single gateway** — e.g. a cheap fast model in `#daily` and a frontier model with a specialist prompt in `#dev`. Configure `channel_overrides` under the platform in `~/.hermes/config.yaml`:
|
||||
|
||||
```yaml
|
||||
platforms:
|
||||
@@ -731,7 +731,7 @@ Once upstream is healthy, `/platform resume <name>` clears the breaker and re-ar
|
||||
|
||||
### Restart notifications
|
||||
|
||||
When the gateway restarts (or is shut down with in-flight sessions), it can send a one-shot "the agent is back" / "the agent was interrupted" message to each platform's home channel. This is controlled per-platform by the `gateway_restart_notification` flag in `gateway-config.yaml`, which defaults to `true`:
|
||||
When the gateway restarts (or is shut down with in-flight sessions), it can send a one-shot "the agent is back" / "the agent was interrupted" message to each platform's home channel. This is controlled per-platform by the `gateway_restart_notification` flag in `config.yaml`, which defaults to `true`:
|
||||
|
||||
```yaml
|
||||
gateway:
|
||||
@@ -748,7 +748,7 @@ Disable it on noisy or low-priority platforms while leaving it on for your prima
|
||||
|
||||
### Typing indicators
|
||||
|
||||
While the agent is processing a message, the gateway shows a live typing status on platforms that support it — a "typing…" bubble on Telegram/Discord/Signal, or the "is thinking…" assistant status on Slack. This is controlled per-platform by the `typing_indicator` flag in `gateway-config.yaml`, which defaults to `true`:
|
||||
While the agent is processing a message, the gateway shows a live typing status on platforms that support it — a "typing…" bubble on Telegram/Discord/Signal, or the "is thinking…" assistant status on Slack. This is controlled per-platform by the `typing_indicator` flag in `config.yaml`, which defaults to `true`:
|
||||
|
||||
```yaml
|
||||
gateway:
|
||||
|
||||
@@ -15,9 +15,9 @@ IRC is plain text: there is no voice, image, file, thread, reaction, typing, or
|
||||
|
||||
## Configure Hermes
|
||||
|
||||
You can configure IRC two ways — environment variables (for a quick env-only setup) or the `gateway` block in `~/.hermes/gateway-config.yaml`.
|
||||
You can configure IRC two ways — environment variables (for a quick env-only setup) or the `gateway` block in `~/.hermes/config.yaml`.
|
||||
|
||||
### Option A — gateway-config.yaml
|
||||
### Option A — config.yaml
|
||||
|
||||
```yaml
|
||||
gateway:
|
||||
|
||||
@@ -1224,8 +1224,8 @@ This covers the custom fallback transport layer that Hermes uses for Telegram co
|
||||
The bot can add emoji reactions to messages as visual processing feedback:
|
||||
|
||||
- 👀 when the bot starts processing your message
|
||||
- ✅ when the response is delivered successfully
|
||||
- ❌ if an error occurs during processing
|
||||
- 👍 when the response is delivered successfully
|
||||
- 👎 if an error occurs during processing
|
||||
|
||||
Reactions are **disabled by default**. Enable them in `config.yaml`:
|
||||
|
||||
@@ -1241,7 +1241,7 @@ TELEGRAM_REACTIONS=true
|
||||
```
|
||||
|
||||
:::note
|
||||
Unlike Discord (where reactions are additive), Telegram's Bot API replaces all bot reactions in a single call. The transition from 👀 to ✅/❌ happens atomically — you won't see both at once.
|
||||
Unlike Discord (where reactions are additive), Telegram's Bot API replaces all bot reactions in a single call. The transition from 👀 to 👍/👎 happens atomically — you won't see both at once.
|
||||
:::
|
||||
|
||||
:::tip
|
||||
|
||||
@@ -176,8 +176,8 @@ hermes gateway install
|
||||
|
||||
What happens under the hood:
|
||||
|
||||
1. `schtasks /Create /SC ONLOGON /RL LIMITED /TN HermesGateway` — registers a task that runs at your login with standard (non-elevated) permissions. No UAC prompt.
|
||||
2. If schtasks is blocked by group policy, falls back to writing a `start /min cmd.exe /d /c <wrapper>` shortcut into `%APPDATA%\Microsoft\Windows\Start Menu\Programs\Startup`. Same effect, slightly cruder.
|
||||
1. `schtasks /Create /SC ONLOGON /RL LIMITED /TN Hermes_Gateway` — registers a task that runs at your login with standard (non-elevated) permissions. No UAC prompt.
|
||||
2. If schtasks is blocked by group policy, falls back to writing a small `Hermes_Gateway.vbs` launcher (run hidden via `wscript.exe`) into `%APPDATA%\Microsoft\Windows\Start Menu\Programs\Startup`. Same effect, slightly cruder. A VBScript is used rather than a `cmd.exe` shortcut because a console allocated at logon can receive a close event that kills the gateway before it finishes starting.
|
||||
3. Spawns the gateway **detached via `pythonw.exe`** — not `python.exe`. `pythonw.exe` has no console attached, which immunizes it against `CTRL_C_EVENT` broadcasts from sibling processes (a real issue that used to kill the gateway when you Ctrl+C'd anything in the same process group).
|
||||
|
||||
Flags used when spawning: `DETACHED_PROCESS | CREATE_NEW_PROCESS_GROUP | CREATE_NO_WINDOW | CREATE_BREAKAWAY_FROM_JOB`.
|
||||
@@ -297,7 +297,7 @@ You hit a shebang-script invocation that bypassed the `.cmd` shim. Hermes resolv
|
||||
Your download of `install.ps1` picked up a UTF-8 BOM. The `irm | iex` form strips BOMs automatically; `[scriptblock]::Create((irm ...))` does not. Re-run with the simple `irm | iex` form, or download the script manually and save it without a BOM via `[IO.File]::WriteAllText($path, $text, (New-Object Text.UTF8Encoding $false))`.
|
||||
|
||||
**Gateway won't stay running after restart.**
|
||||
Check `hermes gateway status` — it merges the schtasks entry, the Startup-folder shortcut (if used), and the live PID. If schtasks is registered but not running, group policy may be blocking `ONLOGON` triggers. Run `schtasks /Query /TN HermesGateway /V /FO LIST` to see the task's failure reason, or fall back to the Startup-folder path by uninstalling and reinstalling with `HERMES_GATEWAY_FORCE_STARTUP=1`.
|
||||
Check `hermes gateway status` — it merges the schtasks entry, the Startup-folder shortcut (if used), and the live PID. If schtasks is registered but not running, group policy may be blocking `ONLOGON` triggers. Run `schtasks /Query /TN Hermes_Gateway /V /FO LIST` (`Hermes_Gateway_<profile>` for a named profile) to see the task's failure reason. The Startup-folder fallback engages automatically only when `schtasks` itself fails to register the task; there is no environment variable or flag to force it.
|
||||
|
||||
**`/edit` still does nothing after setting `$env:EDITOR`.**
|
||||
You set it in the current process only; close and reopen the shell, or set it at User scope in System Properties → Environment Variables. Verify with `echo $env:EDITOR` in a new PowerShell window.
|
||||
|
||||
Reference in New Issue
Block a user